From 139f7c9691a5e5aaa5a47adc041f2be5a5e5504f Mon Sep 17 00:00:00 2001 From: Treffehn Date: Tue, 13 Jun 2023 16:20:05 +0200 Subject: [PATCH 1/7] changed item generation yml file(s) and set up input folder structure for P800-2 as an example --- ... => item_gen_P800-2_HEADacoustics_IKS.yml} | 38 +- .../P800-2/config/item_gen_P800-2_Mesaqin.yml | 399 ++++++++++++++++++ .../selection/P800-2/gen_input/IRs/.gitkeep | 0 .../P800-2/gen_input/items_mono/.gitkeep | 0 4 files changed, 418 insertions(+), 19 deletions(-) rename experiments/selection/P800-2/config/{item_gen_P800-2.yml => item_gen_P800-2_HEADacoustics_IKS.yml} (95%) create mode 100644 experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml create mode 100644 experiments/selection/P800-2/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-2/gen_input/items_mono/.gitkeep diff --git a/experiments/selection/P800-2/config/item_gen_P800-2.yml b/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml similarity index 95% rename from experiments/selection/P800-2/config/item_gen_P800-2.yml rename to experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml index d929ae6c..f4de2380 100644 --- a/experiments/selection/P800-2/config/item_gen_P800-2.yml +++ b/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml @@ -18,10 +18,10 @@ fs: 48000 # IR_fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-2/gen_input/items_mono" ### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' -IR_path: "./IRs" +IR_path: "experiments/selection/P800-2/gen_input/IRs" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-2/proc_input" @@ -37,8 +37,8 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p01" for exp and "g" for provider -listening_lab: "l" -language: "EN" +listening_lab: "b" +language: "GE" exp: "p02" provider: "g" @@ -104,7 +104,7 @@ use_output_prefix: "leee" scenes: cat1_1: - name: "cat1/a1s01" + name: "cat1/a1s01.wav" description: "Car with AB microphone pickup, no overlap between the talkers, car noise." source: ["f1s01.wav", "m1s01.wav"] IR: ["Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos1_Stereo_M5_SinSweep_2chn.wav"] @@ -252,98 +252,98 @@ scenes: cat4_1: name: "cat4/a4s01.wav" - description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m1s07.wav", "f1s07.wav"] IR: ["IR_g_p02_b_01_00_stAB100.wav", "IR_g_p02_b_07_00_stAB100.wav"] overlap: -1.0 cat4_2: name: "cat4/a4s02.wav" - description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f2s07.wav", "m2s07.wav"] IR: ["IR_g_p02_b_05_00_stAB100.wav", "IR_g_p02_b_03_00_stAB100.wav"] overlap: -1.0 cat4_3: name: "cat4/a4s03.wav" - description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m3s07.wav", "f3s07.wav"] IR: ["IR_g_p02_b_02_00_stAB100.wav", "IR_g_p02_b_06_00_stAB100.wav"] overlap: -1.0 cat4_4: name: "cat4/a4s04.wav" - description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f1s08.wav", "m1s08.wav"] IR: ["IR_g_p02_b_04_00_stAB100.wav", "IR_g_p02_b_01_00_stAB100.wav"] overlap: -1.0 cat4_5: name: "cat4/a4s05.wav" - description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m2s08.wav", "f2s08.wav"] IR: ["IR_g_p02_b_03_00_stAB100.wav", "IR_g_p02_b_04_00_stAB100.wav"] overlap: -1.0 cat4_6: name: "cat4/a4s06.wav" - description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f3s08.wav", "m3s08.wav"] IR: ["IR_g_p02_b_07_00_stAB100.wav", "IR_g_p02_b_02_00_stAB100.wav"] overlap: -1.0 cat4_7: name: "cat4/a4s07.wav" - description: "Preliminary: Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Preliminary: Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f1s14.wav", "m1s14.wav"] IR: ["IR_g_p02_b_04_00_stAB100.wav", "IR_g_p02_b_01_00_stAB100.wav"] overlap: -1.0 cat5_1: name: "cat5/a5s01.wav" - description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f3s09.wav", "m3s09.wav"] IR: ["IR_g_p02_d_02_00_stAB150.wav", "IR_g_p02_d_08_00_stAB150.wav"] overlap: -1.0 cat5_2: name: "cat5/a5s02.wav" - description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m1s09.wav", "f1s09.wav"] IR: ["IR_g_p02_d_09_00_stAB150.wav", "IR_g_p02_d_04_00_stAB150.wav"] overlap: -1.0 cat5_3: name: "cat5/a5s03.wav" - description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f2s09.wav", "m2s09.wav"] IR: ["IR_g_p02_d_06_00_stAB150.wav", "IR_g_p02_d_10_00_stAB150.wav"] overlap: -1.0 cat5_4: name: "cat5/a5s04.wav" - description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m3s10.wav", "f3s10.wav"] IR: ["IR_g_p02_d_11_00_stAB150.wav", "IR_g_p02_d_08_00_stAB150.wav"] overlap: -1.0 cat5_5: name: "cat5/a5s05.wav" - description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["f1s10.wav", "m1s10.wav"] IR: ["IR_g_p02_d_10_00_stAB150.wav", "IR_g_p02_d_12_00_stAB150.wav"] overlap: -1.0 cat5_6: name: "cat5/a5s06.wav" - description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m2s10.wav", "f2s10.wav"] IR: ["IR_g_p02_d_12_00_stAB150.wav", "IR_g_p02_d_01_00_stAB150.wav"] overlap: -1.0 cat5_7: name: "cat5/a5s07.wav" - description: "Preliminary: Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise." + description: "Preliminary: Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." source: ["m2s14.wav", "f2s14.wav"] IR: ["IR_g_p02_d_10_00_stAB150.wav", "IR_g_p02_d_12_00_stAB150.wav"] overlap: -1.0 diff --git a/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml b/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml new file mode 100644 index 00000000..6ee39163 --- /dev/null +++ b/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml @@ -0,0 +1,399 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: "STEREO" + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### IR sampling rate in Hz (only for files in .pcm format); default = 48000 +# IR_fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-2/gen_input/items_mono" + +### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' +IR_path: "experiments/selection/P800-2/gen_input/IRs" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-2/proc_input" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p01" for exp and "g" for provider +listening_lab: "d" +language: "MA" +exp: "p02" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all IR filenames (default: "") +### p stands for the 'provider', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +# use_IR_prefix: "IR_pp_eee_" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### IR: filenames(s) of the input IRs (the program will search for it in the IR_path folder) +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### Note 1: use brackets [val1, val2, ...] when specifying multiple values + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the input IR files +### The input IR filenames are represented by: +### IR_pp_eee_r_tt_mm_ffffff.wav +### where: +### pp stands for the provider: do (Dolby), no (Nokia), or (Orange), vo (VoiceAge), g (G.191) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### r stands for the room ID: a, b, c, ... +### tt stands for the talker position: 01, 02, ... +### mm stands for the microphone position: 00, 01, 02, ... +### ffffff stands for the format ID: stAB20, stABC20, stAB100, stAB150, stMS, stBin, FOA, HOA2 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["f1s01.wav", "m1s01.wav"] + IR: ["Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos1_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat1_2: + name: "cat1/a1s02.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["m2s01.wav", "f2s01.wav"] + IR: ["Car_TalkPos2_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat1_3: + name: "cat1/a1s03.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["f3s01.wav", "m3s01.wav"] + IR: ["Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos3_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat1_4: + name: "cat1/a1s04.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["m1s02.wav", "f1s02.wav"] + IR: ["Car_TalkPos4_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat1_5: + name: "cat1/a1s05.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["f2s02.wav", "m2s02.wav"] + IR: ["Car_TalkPos2_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos4_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat1_6: + name: "cat1/a1s06.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["m3s02.wav", "f3s02.wav"] + IR: ["Car_TalkPos3_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos2_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat1_7: + name: "cat1/a1s07" + description: "Preliminary: Car with AB microphone pickup, no overlap between the talkers, car noise." + source: ["f1s13.wav", "m1s13.wav"] + IR: ["Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos1_Stereo_M5_SinSweep_2chn.wav"] + overlap: -1.0 + + cat2_1: + name: "cat2/a2s01.wav" + description: "Car with AB microphone pickup, no overlap between the talkers, street noise." + source: ["m3s03.wav", "f3s03.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos1.wav", "FreeField_IR_Python_AB_20cm_Pos4.wav"] + overlap: -1.0 + + cat2_2: + name: "cat2/a2s02.wav" + description: "Street conversation with AB microphone pickup, no overlap between the talkers, street noise." + source: ["f1s03.wav", "m1s03.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos0.wav", "FreeField_IR_Python_AB_20cm_Pos1.wav"] + overlap: -1.0 + + cat2_3: + name: "cat2/a2s03.wav" + description: "Street conversation with AB microphone pickup, no overlap between the talkers, street noise." + source: ["m2s03.wav", "f2s03.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos2.wav", "FreeField_IR_Python_AB_20cm_Pos0.wav"] + overlap: -1.0 + + cat2_4: + name: "cat2/a2s04.wav" + description: "Street conversation with AB microphone pickup, no overlap between the talkers, street noise." + source: ["f3s04.wav", "m3s04.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos1.wav", "FreeField_IR_Python_AB_20cm_Pos3.wav"] + overlap: -1.0 + + cat2_5: + name: "cat2/a2s05.wav" + description: "Street conversation with AB microphone pickup, no overlap between the talkers, street noise." + source: ["m1s04.wav", "f1s04.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos4.wav", "FreeField_IR_Python_AB_20cm_Pos2.wav"] + overlap: -1.0 + + cat2_6: + name: "cat2/a2s06.wav" + description: "Street conversation with AB microphone pickup, no overlap between the talkers, street noise." + source: ["f2s04.wav", "m2s04.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos3.wav", "FreeField_IR_Python_AB_20cm_Pos0.wav"] + overlap: -1.0 + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: Street conversation with AB microphone pickup, no overlap between the talkers, street noise." + source: ["m2s13.wav", "f2s13.wav"] + IR: ["FreeField_IR_Python_AB_20cm_Pos0.wav", "FreeField_IR_Python_AB_20cm_Pos1.wav"] + overlap: -1.0 + + cat3_1: + name: "cat3/a3s01.wav" + description: "Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["f2s05.wav", "m2s05.wav"] + IR: ["IR_g_p02_b_01_00_stMS100.wav", "IR_g_p02_b_07_00_stMS100.wav"] + overlap: -1.0 + + cat3_2: + name: "cat3/a3s02.wav" + description: "Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["m3s05.wav", "f3s05.wav"] + IR: ["IR_g_p02_b_05_00_stMS100.wav", "IR_g_p02_b_03_00_stMS100.wav"] + overlap: -1.0 + + cat3_3: + name: "cat3/a3s03.wav" + description: "Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["f1s05.wav", "m1s05.wav"] + IR: ["IR_g_p02_b_02_00_stMS100.wav", "IR_g_p02_b_06_00_stMS100.wav"] + overlap: -1.0 + + cat3_4: + name: "cat3/a3s04.wav" + description: "Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["m2s06.wav", "f2s06.wav"] + IR: ["IR_g_p02_b_04_00_stMS100.wav", "IR_g_p02_b_01_00_stMS100.wav"] + overlap: -1.0 + + cat3_5: + name: "cat3/a3s05.wav" + description: "Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["f3s06.wav", "m3s06.wav"] + IR: ["IR_g_p02_b_03_00_stMS100.wav", "IR_g_p02_b_04_00_stMS100.wav"] + overlap: -1.0 + + cat3_6: + name: "cat3/a3s06.wav" + description: "Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["m1s06.wav", "f1s06.wav"] + IR: ["IR_g_p02_b_07_00_stMS100.wav", "IR_g_p02_b_02_00_stMS100.wav"] + overlap: -1.0 + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: Small echoic room with MS microphone pickup, no overlap between the talkers, office noise." + source: ["f3s13.wav", "m3s13.wav"] + IR: ["IR_g_p02_b_02_00_stMS100.wav", "IR_g_p02_b_06_00_stMS100.wav"] + overlap: -1.0 + + cat4_1: + name: "cat4/a4s01.wav" + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m1s07.wav", "f1s07.wav"] + IR: ["IR_g_p02_b_01_00_stAB100.wav", "IR_g_p02_b_07_00_stAB100.wav"] + overlap: -1.0 + + cat4_2: + name: "cat4/a4s02.wav" + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f2s07.wav", "m2s07.wav"] + IR: ["IR_g_p02_b_05_00_stAB100.wav", "IR_g_p02_b_03_00_stAB100.wav"] + overlap: -1.0 + + cat4_3: + name: "cat4/a4s03.wav" + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m3s07.wav", "f3s07.wav"] + IR: ["IR_g_p02_b_02_00_stAB100.wav", "IR_g_p02_b_06_00_stAB100.wav"] + overlap: -1.0 + + cat4_4: + name: "cat4/a4s04.wav" + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f1s08.wav", "m1s08.wav"] + IR: ["IR_g_p02_b_04_00_stAB100.wav", "IR_g_p02_b_01_00_stAB100.wav"] + overlap: -1.0 + + cat4_5: + name: "cat4/a4s05.wav" + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m2s08.wav", "f2s08.wav"] + IR: ["IR_g_p02_b_03_00_stAB100.wav", "IR_g_p02_b_04_00_stAB100.wav"] + overlap: -1.0 + + cat4_6: + name: "cat4/a4s06.wav" + description: "Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f3s08.wav", "m3s08.wav"] + IR: ["IR_g_p02_b_07_00_stAB100.wav", "IR_g_p02_b_02_00_stAB100.wav"] + overlap: -1.0 + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: Small echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f1s14.wav", "m1s14.wav"] + IR: ["IR_g_p02_b_04_00_stAB100.wav", "IR_g_p02_b_01_00_stAB100.wav"] + overlap: -1.0 + + cat5_1: + name: "cat5/a5s01.wav" + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f3s09.wav", "m3s09.wav"] + IR: ["IR_g_p02_d_02_00_stAB150.wav", "IR_g_p02_d_08_00_stAB150.wav"] + overlap: -1.0 + + cat5_2: + name: "cat5/a5s02.wav" + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m1s09.wav", "f1s09.wav"] + IR: ["IR_g_p02_d_09_00_stAB150.wav", "IR_g_p02_d_04_00_stAB150.wav"] + overlap: -1.0 + + cat5_3: + name: "cat5/a5s03.wav" + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f2s09.wav", "m2s09.wav"] + IR: ["IR_g_p02_d_06_00_stAB150.wav", "IR_g_p02_d_10_00_stAB150.wav"] + overlap: -1.0 + + cat5_4: + name: "cat5/a5s04.wav" + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m3s10.wav", "f3s10.wav"] + IR: ["IR_g_p02_d_11_00_stAB150.wav", "IR_g_p02_d_08_00_stAB150.wav"] + overlap: -1.0 + + cat5_5: + name: "cat5/a5s05.wav" + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["f1s10.wav", "m1s10.wav"] + IR: ["IR_g_p02_d_10_00_stAB150.wav", "IR_g_p02_d_12_00_stAB150.wav"] + overlap: -1.0 + + cat5_6: + name: "cat5/a5s06.wav" + description: "Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m2s10.wav", "f2s10.wav"] + IR: ["IR_g_p02_d_12_00_stAB150.wav", "IR_g_p02_d_01_00_stAB150.wav"] + overlap: -1.0 + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: Large echoic room with AB microphone pickup, no overlap between the talkers, office noise." + source: ["m2s14.wav", "f2s14.wav"] + IR: ["IR_g_p02_d_10_00_stAB150.wav", "IR_g_p02_d_12_00_stAB150.wav"] + overlap: -1.0 + + cat6_1: + name: "cat6/a6s01.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["m2s11.wav", "f2s11.wav"] + IR: ["IR_g_p02_b_01_00_stBI100.wav", "IR_g_p02_b_07_00_stBI100.wav"] + overlap: -1.0 + + cat6_2: + name: "cat6/a6s02.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["f3s11.wav", "m3s11.wav"] + IR: ["IR_g_p02_b_05_00_stBI100.wav", "IR_g_p02_b_03_00_stBI100.wav"] + overlap: -1.0 + + cat6_3: + name: "cat6/a6s03.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["m1s11.wav", "f1s11.wav"] + IR: ["IR_g_p02_b_02_00_stBI100.wav", "IR_g_p02_b_06_00_stBI100.wav"] + overlap: -1.0 + + cat6_4: + name: "cat6/a6s04.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["f2s12.wav", "m2s12.wav"] + IR: ["IR_g_p02_b_04_00_stBI100.wav", "IR_g_p02_b_01_00_stBI100.wav"] + overlap: -1.0 + + cat6_5: + name: "cat6/a6s05.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["m3s12.wav", "f3s12.wav"] + IR: ["IR_g_p02_b_03_00_stBI100.wav", "IR_g_p02_b_04_00_stBI100.wav"] + overlap: -1.0 + + cat6_6: + name: "cat6/a6s06.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["f1s12.wav", "m1s12.wav"] + IR: ["IR_g_p02_b_07_00_stBI100.wav", "IR_g_p02_b_02_00_stBI100.wav"] + overlap: -1.0 + + cat6_7: + name: "cat6/a6s07.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers, office noise." + source: ["f3s14.wav", "m3s14.wav"] + IR: ["IR_g_p02_b_07_00_stBI100.wav", "IR_g_p02_b_02_00_stBI100.wav"] + overlap: -1.0 + \ No newline at end of file diff --git a/experiments/selection/P800-2/gen_input/IRs/.gitkeep b/experiments/selection/P800-2/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-2/gen_input/items_mono/.gitkeep b/experiments/selection/P800-2/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b -- GitLab From 5420d6ce44a9266789afc9f6b25f71c456a915f4 Mon Sep 17 00:00:00 2001 From: Treffehn Date: Wed, 14 Jun 2023 12:18:32 +0200 Subject: [PATCH 2/7] modified gitignore and item gen P800-2 configs --- .gitignore | 5 +++++ .../P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml | 2 +- .../selection/P800-2/config/item_gen_P800-2_Mesaqin.yml | 2 +- experiments/selection/P800-2/gen_input/.gitkeep | 0 4 files changed, 7 insertions(+), 2 deletions(-) create mode 100644 experiments/selection/P800-2/gen_input/.gitkeep diff --git a/.gitignore b/.gitignore index bb354bbe..21355b56 100644 --- a/.gitignore +++ b/.gitignore @@ -14,8 +14,13 @@ mc.double experiments/selection/*/proc_input/cat*/*.wav experiments/selection/*/proc_input/cat*/*.csv experiments/selection/*/proc_input/cat*/*.pcm +experiments/selection/*/background_noise/*.wav +experiments/selection/*/proc_input/*.log +experiments/selection/*/proc_input/*.yml experiments/selection/*/proc_output/ experiments/selection/*/config/*cat*-lab_*.yml +experiments/selection/*/gen_input/IRs/*.wav +experiments/selection/*/gen_input/items_mono/*.wav *~ tests/temp_output_* tests/cut diff --git a/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml b/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml index f4de2380..b51b6cc7 100644 --- a/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml +++ b/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml @@ -146,7 +146,7 @@ scenes: overlap: -1.0 cat1_7: - name: "cat1/a1s07" + name: "cat1/a1s07.wav" description: "Preliminary: Car with AB microphone pickup, no overlap between the talkers, car noise." source: ["f1s13.wav", "m1s13.wav"] IR: ["Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos1_Stereo_M5_SinSweep_2chn.wav"] diff --git a/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml b/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml index 6ee39163..923778e6 100644 --- a/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml +++ b/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml @@ -146,7 +146,7 @@ scenes: overlap: -1.0 cat1_7: - name: "cat1/a1s07" + name: "cat1/a1s07.wav" description: "Preliminary: Car with AB microphone pickup, no overlap between the talkers, car noise." source: ["f1s13.wav", "m1s13.wav"] IR: ["Car_TalkPos5_Stereo_M5_SinSweep_2chn.wav", "Car_TalkPos1_Stereo_M5_SinSweep_2chn.wav"] diff --git a/experiments/selection/P800-2/gen_input/.gitkeep b/experiments/selection/P800-2/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b -- GitLab From 6ef92ad043f11dbf7adfa03a4fb048ab06fd9aa1 Mon Sep 17 00:00:00 2001 From: Treffehn Date: Wed, 14 Jun 2023 13:41:15 +0200 Subject: [PATCH 3/7] added info in readme --- README.md | 37 ++++++++++++++++++- ...coustics_IKS.yml => item_gen_P800-2_b.yml} | 0 ...00-2_Mesaqin.yml => item_gen_P800-2_d.yml} | 0 3 files changed, 36 insertions(+), 1 deletion(-) rename experiments/selection/P800-2/config/{item_gen_P800-2_HEADacoustics_IKS.yml => item_gen_P800-2_b.yml} (100%) rename experiments/selection/P800-2/config/{item_gen_P800-2_Mesaqin.yml => item_gen_P800-2_d.yml} (100%) diff --git a/README.md b/README.md index 5d1421d1..bc2c6b75 100755 --- a/README.md +++ b/README.md @@ -47,6 +47,41 @@ --- +# Quick guide: How to set up a listening test + +The setup for a listening test from the experiments folder according to the Processing Plan (IVAS-7) and Test Plan (IVAS-8) consists of two steps: +item generation and item processing. +In the following sections the only purpose of the curly brackets is to mark the variables that thave to be replaced with the actual values. + +## P800 + +### Item generation + +To set up the P800-{X} listening test (X = 1, 2, ...9) copy your mono input files to 'experiments/selection/P800-{X}/gen_input/items_mono'. +These files have to follow the naming scheme '{l}{LL}p0{X}{name_of_item}' where 'l' stands for the listening lab designator: a (Force Technology), +b (HEAD acoustics), c (MQ University), d (Mesaqin.com), and 'LL' stands for the language: EN, GE, JA, MA, DA, FR. + +The impluse responses have to be copied to experiments/selection/P800-{X}/gen_input/IRs. + +To generate the items run `python -m ivas_processing_scripts.generation experiments/P800-{X}/config/item_gen_P800-{X}_{l}.yml` from the root folder of the repository. +The resulting files can be found in 'experiments/selection/P800-{X}/proc_input' sorted by category. + +### Item processing + +If the tests includes background noise, the corresponding files have to be copied to 'experiments/selection/P800-{X}/background_noise'. +The naming has to follow the scheme 'background_noise_cat{c}.wav' where 'c' denotes the category with a number between one and six. + +To process the items run `python -m generate_test.py P800-{X},{l}` from the root folder of this repository. +The results can be found in 'experiments/selection/P800-{X}/proc_output'. + +For more information about this processing step see +[How to generate the configs and process items for the selection test experiments](#how-to-generate-the-configs-and-process-items-for-the-selection-test-experiments). + +# MUSHRA +todo + +--- + # Item generation The `item_generation_scripts` module may be used to generate audio items for the P.800 listening test according to the scene description. All scenes must be fully described in the `SCENE.yml` file. The module takes monophonic audio @@ -706,7 +741,7 @@ options: --no_parallel If given, configs will not be run in parallel --create_cfg_only If given, only create the configs and folder structure without processing items ``` -Before running the script, one needs to put the input files in the respective input folder (including the background noise files, see below). If input files are missing, the script will complain ad stop. For example, for processing tests P800-3 and BS1534-4a for labs b and d, respectively, command line would look like this (no whitespace between the commas!): +Before running the script, one needs to put the input files in the respective input folder (including the background noise files, see below). If input files are missing, the script will complain and stop. For example, for processing tests P800-3 and BS1534-4a for labs b and d, respectively, command line would look like this (no whitespace between the commas!): ``` python3 generate_test.py P800-3,b BS1534-4a,d ``` diff --git a/experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml b/experiments/selection/P800-2/config/item_gen_P800-2_b.yml similarity index 100% rename from experiments/selection/P800-2/config/item_gen_P800-2_HEADacoustics_IKS.yml rename to experiments/selection/P800-2/config/item_gen_P800-2_b.yml diff --git a/experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml b/experiments/selection/P800-2/config/item_gen_P800-2_d.yml similarity index 100% rename from experiments/selection/P800-2/config/item_gen_P800-2_Mesaqin.yml rename to experiments/selection/P800-2/config/item_gen_P800-2_d.yml -- GitLab From 449453b86d2a2b1d8b728c00ed9d6c6be3efbd30 Mon Sep 17 00:00:00 2001 From: Treffehn Date: Thu, 15 Jun 2023 09:54:48 +0200 Subject: [PATCH 4/7] added file structure to the other P800 tests --- README.md | 2 +- experiments/selection/P800-1/gen_input/.gitkeep | 0 experiments/selection/P800-1/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-1/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-3/gen_input/.gitkeep | 0 experiments/selection/P800-3/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-3/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-4/gen_input/.gitkeep | 0 experiments/selection/P800-4/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-4/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-5/gen_input/.gitkeep | 0 experiments/selection/P800-5/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-5/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-6/gen_input/.gitkeep | 0 experiments/selection/P800-6/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-6/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-7/gen_input/.gitkeep | 0 experiments/selection/P800-7/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-7/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-8/gen_input/.gitkeep | 0 experiments/selection/P800-8/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-8/gen_input/items_mono/.gitkeep | 0 experiments/selection/P800-9/gen_input/.gitkeep | 0 experiments/selection/P800-9/gen_input/IRs/.gitkeep | 0 experiments/selection/P800-9/gen_input/items_mono/.gitkeep | 0 25 files changed, 1 insertion(+), 1 deletion(-) create mode 100644 experiments/selection/P800-1/gen_input/.gitkeep create mode 100644 experiments/selection/P800-1/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-1/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-3/gen_input/.gitkeep create mode 100644 experiments/selection/P800-3/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-3/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-4/gen_input/.gitkeep create mode 100644 experiments/selection/P800-4/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-4/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-5/gen_input/.gitkeep create mode 100644 experiments/selection/P800-5/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-5/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-6/gen_input/.gitkeep create mode 100644 experiments/selection/P800-6/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-6/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-7/gen_input/.gitkeep create mode 100644 experiments/selection/P800-7/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-7/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-8/gen_input/.gitkeep create mode 100644 experiments/selection/P800-8/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-8/gen_input/items_mono/.gitkeep create mode 100644 experiments/selection/P800-9/gen_input/.gitkeep create mode 100644 experiments/selection/P800-9/gen_input/IRs/.gitkeep create mode 100644 experiments/selection/P800-9/gen_input/items_mono/.gitkeep diff --git a/README.md b/README.md index bc2c6b75..59e67e65 100755 --- a/README.md +++ b/README.md @@ -71,7 +71,7 @@ The resulting files can be found in 'experiments/selection/P800-{X}/proc_input' If the tests includes background noise, the corresponding files have to be copied to 'experiments/selection/P800-{X}/background_noise'. The naming has to follow the scheme 'background_noise_cat{c}.wav' where 'c' denotes the category with a number between one and six. -To process the items run `python -m generate_test.py P800-{X},{l}` from the root folder of this repository. +To process the items run `python generate_test.py P800-{X},{l}` from the root folder of this repository. The results can be found in 'experiments/selection/P800-{X}/proc_output'. For more information about this processing step see diff --git a/experiments/selection/P800-1/gen_input/.gitkeep b/experiments/selection/P800-1/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-1/gen_input/IRs/.gitkeep b/experiments/selection/P800-1/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-1/gen_input/items_mono/.gitkeep b/experiments/selection/P800-1/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-3/gen_input/.gitkeep b/experiments/selection/P800-3/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-3/gen_input/IRs/.gitkeep b/experiments/selection/P800-3/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-3/gen_input/items_mono/.gitkeep b/experiments/selection/P800-3/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-4/gen_input/.gitkeep b/experiments/selection/P800-4/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-4/gen_input/IRs/.gitkeep b/experiments/selection/P800-4/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-4/gen_input/items_mono/.gitkeep b/experiments/selection/P800-4/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-5/gen_input/.gitkeep b/experiments/selection/P800-5/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-5/gen_input/IRs/.gitkeep b/experiments/selection/P800-5/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-5/gen_input/items_mono/.gitkeep b/experiments/selection/P800-5/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-6/gen_input/.gitkeep b/experiments/selection/P800-6/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-6/gen_input/IRs/.gitkeep b/experiments/selection/P800-6/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-6/gen_input/items_mono/.gitkeep b/experiments/selection/P800-6/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-7/gen_input/.gitkeep b/experiments/selection/P800-7/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-7/gen_input/IRs/.gitkeep b/experiments/selection/P800-7/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-7/gen_input/items_mono/.gitkeep b/experiments/selection/P800-7/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-8/gen_input/.gitkeep b/experiments/selection/P800-8/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-8/gen_input/IRs/.gitkeep b/experiments/selection/P800-8/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-8/gen_input/items_mono/.gitkeep b/experiments/selection/P800-8/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-9/gen_input/.gitkeep b/experiments/selection/P800-9/gen_input/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-9/gen_input/IRs/.gitkeep b/experiments/selection/P800-9/gen_input/IRs/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/experiments/selection/P800-9/gen_input/items_mono/.gitkeep b/experiments/selection/P800-9/gen_input/items_mono/.gitkeep new file mode 100644 index 00000000..e69de29b -- GitLab From eebea347f7bfed12e728d7c55bd1e652e370e8fc Mon Sep 17 00:00:00 2001 From: Treffehn Date: Thu, 15 Jun 2023 10:18:50 +0200 Subject: [PATCH 5/7] added config files for different labs --- ...m_gen_P800-1.yml => item_gen_P800-1_a.yml} | 8 +- .../P800-1/config/item_gen_P800-1_d.yml | 400 ++++++++++++++++ .../P800-4/config/item_gen_P800-4_a.yml | 445 ++++++++++++++++++ ...m_gen_P800-4.yml => item_gen_P800-4_c.yml} | 6 +- ...m_gen_P800-5.yml => item_gen_P800-5_a.yml} | 8 +- .../P800-5/config/item_gen_P800-5_b.yml | 445 ++++++++++++++++++ .../P800-6/config/item_gen_P800-6_a.yml | 424 +++++++++++++++++ ...m_gen_P800-6.yml => item_gen_P800-6_c.yml} | 4 +- .../selection/P800-6/gen_input/IRs/.gitkeep | 0 ...m_gen_P800-7.yml => item_gen_P800-7_a.yml} | 6 +- .../P800-7/config/item_gen_P800-7_d.yml | 423 +++++++++++++++++ .../selection/P800-7/gen_input/IRs/.gitkeep | 0 ...m_gen_P800-8.yml => item_gen_P800-8_a.yml} | 8 +- .../P800-8/config/item_gen_P800-8_b.yml | 445 ++++++++++++++++++ ...m_gen_P800-9.yml => item_gen_P800-9_a.yml} | 8 +- .../P800-9/config/item_gen_P800-9_d.yml | 445 ++++++++++++++++++ 16 files changed, 3051 insertions(+), 24 deletions(-) rename experiments/selection/P800-1/config/{item_gen_P800-1.yml => item_gen_P800-1_a.yml} (99%) create mode 100644 experiments/selection/P800-1/config/item_gen_P800-1_d.yml create mode 100644 experiments/selection/P800-4/config/item_gen_P800-4_a.yml rename experiments/selection/P800-4/config/{item_gen_P800-4.yml => item_gen_P800-4_c.yml} (99%) rename experiments/selection/P800-5/config/{item_gen_P800-5.yml => item_gen_P800-5_a.yml} (99%) create mode 100644 experiments/selection/P800-5/config/item_gen_P800-5_b.yml create mode 100644 experiments/selection/P800-6/config/item_gen_P800-6_a.yml rename experiments/selection/P800-6/config/{item_gen_P800-6.yml => item_gen_P800-6_c.yml} (99%) delete mode 100644 experiments/selection/P800-6/gen_input/IRs/.gitkeep rename experiments/selection/P800-7/config/{item_gen_P800-7.yml => item_gen_P800-7_a.yml} (99%) create mode 100644 experiments/selection/P800-7/config/item_gen_P800-7_d.yml delete mode 100644 experiments/selection/P800-7/gen_input/IRs/.gitkeep rename experiments/selection/P800-8/config/{item_gen_P800-8.yml => item_gen_P800-8_a.yml} (99%) create mode 100644 experiments/selection/P800-8/config/item_gen_P800-8_b.yml rename experiments/selection/P800-9/config/{item_gen_P800-9.yml => item_gen_P800-9_a.yml} (99%) create mode 100644 experiments/selection/P800-9/config/item_gen_P800-9_d.yml diff --git a/experiments/selection/P800-1/config/item_gen_P800-1.yml b/experiments/selection/P800-1/config/item_gen_P800-1_a.yml similarity index 99% rename from experiments/selection/P800-1/config/item_gen_P800-1.yml rename to experiments/selection/P800-1/config/item_gen_P800-1_a.yml index 6b89a00d..a7fc6220 100644 --- a/experiments/selection/P800-1/config/item_gen_P800-1.yml +++ b/experiments/selection/P800-1/config/item_gen_P800-1_a.yml @@ -18,10 +18,10 @@ fs: 48000 # IR_fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-1/gen_input/items_mono" ### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' -IR_path: "./IRs" +IR_path: "experiments/selection/P800-1/gen_input/IRs" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-1/proc_input" @@ -37,8 +37,8 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p01" for exp and "g" for provider -listening_lab: "l" -language: "EN" +listening_lab: "a" +language: "JA" exp: "p01" provider: "g" diff --git a/experiments/selection/P800-1/config/item_gen_P800-1_d.yml b/experiments/selection/P800-1/config/item_gen_P800-1_d.yml new file mode 100644 index 00000000..4b17c40f --- /dev/null +++ b/experiments/selection/P800-1/config/item_gen_P800-1_d.yml @@ -0,0 +1,400 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths + +### Output format +format: "STEREO" + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### IR sampling rate in Hz (only for files in .pcm format); default = 48000 +# IR_fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-1/gen_input/items_mono" + +### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' +IR_path: "experiments/selection/P800-1/gen_input/IRs" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-1/proc_input" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = False (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p01" for exp and "g" for provider +listening_lab: "d" +language: "FR" +exp: "p01" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all IR filenames (default: "") +### p stands for the 'provider', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +# use_IR_prefix: "IR_pp_eee_" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### IR: filenames(s) of the input IRs (the program will search for it in the IR_path folder) +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### Note 1: use brackets [val1, val2, ...] when specifying multiple values + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the input IR files +### The input IR filenames are represented by: +### IR_pp_eee_r_tt_mm_ffffff.wav +### where: +### pp stands for the provider: do (Dolby), no (Nokia), or (Orange), vo (VoiceAge), g (G.191) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### r stands for the room ID: a, b, c, ... +### tt stands for the talker position: 01, 02, ... +### mm stands for the microphone position: 00, 01, 02, ... +### ffffff stands for the format ID: stAB20, stABC20, stAB100, stAB150, stMS, stBin, FOA, HOA2 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f1s01.wav", "m1s01.wav"] + IR: ["IR_g_p01_a_01_00_stAB100.wav", "IR_g_p01_a_07_00_stAB100.wav"] + overlap: 1.0 + + cat1_2: + name: "cat1/a1s02.wav" + description: "Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m2s01.wav", "f2s01.wav"] + IR: ["IR_g_p01_a_05_00_stAB100.wav", "IR_g_p01_a_03_00_stAB100.wav"] + overlap: 1.0 + + cat1_3: + name: "cat1/a1s03.wav" + description: "Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f3s01.wav", "m3s01.wav"] + IR: ["IR_g_p01_a_02_00_stAB100.wav", "IR_g_p01_a_06_00_stAB100.wav"] + overlap: 1.0 + + cat1_4: + name: "cat1/a1s04.wav" + description: "Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m1s02.wav", "f1s02.wav"] + IR: ["IR_g_p01_a_04_00_stAB100.wav", "IR_g_p01_a_01_00_stAB100.wav"] + overlap: 1.0 + + cat1_5: + name: "cat1/a1s05.wav" + description: "Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f2s02.wav", "m2s02.wav"] + IR: ["IR_g_p01_a_03_00_stAB100.wav", "IR_g_p01_a_04_00_stAB100.wav"] + overlap: 1.0 + + cat1_6: + name: "cat1/a1s06.wav" + description: "Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m3s02.wav", "f3s02.wav"] + IR: ["IR_g_p01_a_07_00_stAB100.wav", "IR_g_p01_a_02_00_stAB100.wav"] + overlap: 1.0 + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: Small anechoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f1s13.wav", "m1s13.wav"] + IR: ["IR_g_p01_a_01_00_stAB100.wav", "IR_g_p01_a_07_00_stAB100.wav"] + overlap: 1.0 + + cat2_1: + name: "cat2/a2s01.wav" + description: "Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["m3s03.wav", "f3s03.wav"] + IR: ["IR_g_p01_c_05_00_stAB150.wav", "IR_g_p01_c_11_00_stAB150.wav"] + overlap: -1.0 + + cat2_2: + name: "cat2/a2s02.wav" + description: "Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["f1s03.wav", "m1s03.wav"] + IR: ["IR_g_p01_c_01_00_stAB150.wav", "IR_g_p01_c_06_00_stAB150.wav"] + overlap: -1.0 + + cat2_3: + name: "cat2/a2s03.wav" + description: "Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["m2s03.wav", "f2s03.wav"] + IR: ["IR_g_p01_c_03_00_stAB150.wav", "IR_g_p01_c_07_00_stAB150.wav"] + overlap: -1.0 + + cat2_4: + name: "cat2/a2s04.wav" + description: "Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["f3s04.wav", "m3s04.wav"] + IR: ["IR_g_p01_c_05_00_stAB150.wav", "IR_g_p01_c_08_00_stAB150.wav"] + overlap: -1.0 + + cat2_5: + name: "cat2/a2s05.wav" + description: "Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["m1s04.wav", "f1s04.wav"] + IR: ["IR_g_p01_c_09_00_stAB150.wav", "IR_g_p01_c_07_00_stAB150.wav"] + overlap: -1.0 + + cat2_6: + name: "cat2/a2s06.wav" + description: "Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["f2s04.wav", "m2s04.wav"] + IR: ["IR_g_p01_c_10_00_stAB150.wav", "IR_g_p01_c_09_00_stAB150.wav"] + overlap: -1.0 + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: Large anechoic room with AB microphone pickup, no overlap between the talkers." + source: ["m2s13.wav", "f2s13.wav"] + IR: ["IR_g_p01_c_05_00_stAB150.wav", "IR_g_p01_c_11_00_stAB150.wav"] + overlap: -1.0 + + cat3_1: + name: "cat3/a3s01.wav" + description: "Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["f2s05.wav", "m2s05.wav"] + IR: ["IR_g_p01_a_01_00_stMS100.wav", "IR_g_p01_a_07_00_stMS100.wav"] + overlap: -1.0 + + cat3_2: + name: "cat3/a3s02.wav" + description: "Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["m3s05.wav", "f3s05.wav"] + IR: ["IR_g_p01_a_05_00_stMS100.wav", "IR_g_p01_a_03_00_stMS100.wav"] + overlap: -1.0 + + cat3_3: + name: "cat3/a3s03.wav" + description: "Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["f1s05.wav", "m1s05.wav"] + IR: ["IR_g_p01_a_02_00_stMS100.wav", "IR_g_p01_a_06_00_stMS100.wav"] + overlap: -1.0 + + cat3_4: + name: "cat3/a3s04.wav" + description: "Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["m2s06.wav", "f2s06.wav"] + IR: ["IR_g_p01_a_04_00_stMS100.wav", "IR_g_p01_a_01_00_stMS100.wav"] + overlap: -1.0 + + cat3_5: + name: "cat3/a3s05.wav" + description: "Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["f3s06.wav", "m3s06.wav"] + IR: ["IR_g_p01_a_03_00_stMS100.wav", "IR_g_p01_a_04_00_stMS100.wav"] + overlap: -1.0 + + cat3_6: + name: "cat3/a3s06.wav" + description: "Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["m1s06.wav", "f1s06.wav"] + IR: ["IR_g_p01_a_07_00_stMS100.wav", "IR_g_p01_a_02_00_stMS100.wav"] + overlap: -1.0 + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: Small anechoic room with MS microphone pickup, no overlap between the talkers." + source: ["f3s13.wav", "m3s13.wav"] + IR: ["IR_g_p01_a_02_00_stMS100.wav", "IR_g_p01_a_06_00_stMS100.wav"] + overlap: -1.0 + + cat4_1: + name: "cat4/a4s01.wav" + description: "Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m1s07.wav", "f1s07.wav"] + IR: ["IR_g_p01_b_01_00_stAB100.wav", "IR_g_p01_b_07_00_stAB100.wav"] + overlap: 1.0 + + cat4_2: + name: "cat4/a4s02.wav" + description: "Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f2s07.wav", "m2s07.wav"] + IR: ["IR_g_p01_b_07_00_stAB100.wav", "IR_g_p01_b_03_00_stAB100.wav"] + overlap: 1.0 + + cat4_3: + name: "cat4/a4s03.wav" + description: "Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m3s07.wav", "f3s07.wav"] + IR: ["IR_g_p01_b_02_00_stAB100.wav", "IR_g_p01_b_06_00_stAB100.wav"] + overlap: 1.0 + + cat4_4: + name: "cat4/a4s04.wav" + description: "Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f1s08.wav", "m1s08.wav"] + IR: ["IR_g_p01_b_04_00_stAB100.wav", "IR_g_p01_b_01_00_stAB100.wav"] + overlap: 1.0 + + cat4_5: + name: "cat4/a4s05.wav" + description: "Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m2s08.wav", "f2s08.wav"] + IR: ["IR_g_p01_b_03_00_stAB100.wav", "IR_g_p01_b_04_00_stAB100.wav"] + overlap: 1.0 + + cat4_6: + name: "cat4/a4s06.wav" + description: "Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f3s08.wav", "m3s08.wav"] + IR: ["IR_g_p01_b_07_00_stAB100.wav", "IR_g_p01_b_02_00_stAB100.wav"] + overlap: 1.0 + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: Small echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m1s14.wav", "f1s14.wav"] + IR: ["IR_g_p01_b_04_00_stAB100.wav", "IR_g_p01_b_01_00_stAB100.wav"] + overlap: 1.0 + + cat5_1: + name: "cat5/a5s01.wav" + description: "Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f3s09.wav", "m3s09.wav"] + IR: ["IR_g_p01_d_02_00_stAB150.wav", "IR_g_p01_d_08_00_stAB150.wav"] + overlap: 1.0 + + cat5_2: + name: "cat5/a5s02.wav" + description: "Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m1s09.wav", "f1s09.wav"] + IR: ["IR_g_p01_d_09_00_stAB150.wav", "IR_g_p01_d_04_00_stAB150.wav"] + overlap: 1.0 + + cat5_3: + name: "cat5/a5s03.wav" + description: "Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f2s09.wav", "m2s09.wav"] + IR: ["IR_g_p01_d_06_00_stAB150.wav", "IR_g_p01_d_10_00_stAB150.wav"] + overlap: 1.0 + + cat5_4: + name: "cat5/a5s04.wav" + description: "Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m3s10.wav", "f3s10.wav"] + IR: ["IR_g_p01_d_11_00_stAB150.wav", "IR_g_p01_d_08_00_stAB150.wav"] + overlap: 1.0 + + cat5_5: + name: "cat5/a5s05.wav" + description: "Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f1s10.wav", "m1s10.wav"] + IR: ["IR_g_p01_d_10_00_stAB150.wav", "IR_g_p01_d_12_00_stAB150.wav"] + overlap: 1.0 + + cat5_6: + name: "cat5/a5s06.wav" + description: "Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["m2s10.wav", "f2s10.wav"] + IR: ["IR_g_p01_d_12_00_stAB150.wav", "IR_g_p01_d_01_00_stAB150.wav"] + overlap: 1.0 + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: Large echoic room with AB microphone pickup, partial overlap between the talkers." + source: ["f2s14.wav", "m2s14.wav"] + IR: ["IR_g_p01_d_10_00_stAB150.wav", "IR_g_p01_d_12_00_stAB150.wav"] + overlap: 1.0 + + cat6_1: + name: "cat6/a6s01.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["m2s11.wav", "f2s11.wav"] + IR: ["IR_g_p01_b_01_00_stBI100.wav", "IR_g_p01_b_07_00_stBI100.wav"] + overlap: -1.0 + + cat6_2: + name: "cat6/a6s02.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["f3s11.wav", "m3s11.wav"] + IR: ["IR_g_p01_b_05_00_stBI100.wav", "IR_g_p01_b_03_00_stBI100.wav"] + overlap: -1.0 + + cat6_3: + name: "cat6/a6s03.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["m1s11.wav", "f1s11.wav"] + IR: ["IR_g_p01_b_02_00_stBI100.wav", "IR_g_p01_b_06_00_stBI100.wav"] + overlap: -1.0 + + cat6_4: + name: "cat6/a6s04.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["f2s12.wav", "m2s12.wav"] + IR: ["IR_g_p01_b_04_00_stBI100.wav", "IR_g_p01_b_01_00_stBI100.wav"] + overlap: -1.0 + + cat6_5: + name: "cat6/a6s05.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["m3s12.wav", "f3s12.wav"] + IR: ["IR_g_p01_b_03_00_stBI100.wav", "IR_g_p01_b_04_00_stBI100.wav"] + overlap: -1.0 + + cat6_6: + name: "cat6/a6s06.wav" + description: "Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["f1s12.wav", "m1s12.wav"] + IR: ["IR_g_p01_b_07_00_stBI100.wav", "IR_g_p01_b_02_00_stBI100.wav"] + overlap: -1.0 + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary: Small echoic room with binaural microphone pickup, no overlap between the talkers." + source: ["m2s14.wav", "f2s14.wav"] + IR: ["IR_g_p01_b_07_00_stBI100.wav", "IR_g_p01_b_02_00_stBI100.wav"] + overlap: -1.0 diff --git a/experiments/selection/P800-4/config/item_gen_P800-4_a.yml b/experiments/selection/P800-4/config/item_gen_P800-4_a.yml new file mode 100644 index 00000000..8de40f24 --- /dev/null +++ b/experiments/selection/P800-4/config/item_gen_P800-4_a.yml @@ -0,0 +1,445 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: "FOA" + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### IR sampling rate in Hz (only for files in .pcm format); default = 48000 +# IR_fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-4/gen_input/items_mono" + +### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' +IR_path: "experiments/selection/P800-4/gen_input/IRs" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-4/proc_input" + +### (Optional) Output path for binauralized versions of the generated FOA items +# binaural_path: "./items_FOA_bin" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider +listening_lab: "a" +language: "JA" +exp: "p04" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all IR filenames (default: "") +### p stands for the 'provider', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +# use_IR_prefix: "IR_pp_eee_" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### IR: filenames(s) of the input IRs (the program will search for it in the IR_path folder) +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### format: input file format ("FOA" or "HOA2") +### Note 1: use brackets [val1, val2, ...] when specifying multiple values + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the input IR files +### The input IR filenames are represented by: +### IR_pp_eee_r_tt_mm_ffffff.wav +### where: +### pp stands for the provider: do (Dolby), no (Nokia), or (Orange), vo (VoiceAge), g (G.191) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### r stands for the room ID: a, b, c, ... +### tt stands for the talker position: 01, 02, ... +### mm stands for the microphone position: 00, 01, 02, ... +### ffffff stands for the format ID: stAB20, stABC20, stAB100, stAB150, stMS, stBin, FOA, HOA2 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "Room 1 with clean background" + source: ["f1s01.wav", "m1s01.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat1_2: + name: "cat1/a1s02.wav" + description: "Room 1 with clean background" + source: ["m2s01.wav", "f2s01.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat1_3: + name: "cat1/a1s03.wav" + description: "Room 1 with clean background" + source: ["f3s01.wav", "m3s01.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat1_4: + name: "cat1/a1s04.wav" + description: "Room 1 with clean background" + source: ["m1s02.wav", "f1s02.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat1_5: + name: "cat1/a1s05.wav" + description: "Room 1 with clean background" + source: ["f2s02.wav", "m2s02.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat1_6: + name: "cat1/a1s06.wav" + description: "Room 1 with clean background" + source: ["m3s02.wav", "f3s02.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: Room 1 with clean background" + source: ["f1s13.wav", "m1s13.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat2_1: + name: "cat2/a2s01.wav" + description: "Room 4 with clean background" + source: ["m3s03.wav", "f3s03.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_2: + name: "cat2/a2s02.wav" + description: "Room 4 with clean background" + source: ["f1s03.wav", "m1s03.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_3: + name: "cat2/a2s03.wav" + description: "Room 4 with clean background" + source: ["m2s03.wav", "f2s03.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_4: + name: "cat2/a2s04.wav" + description: "Room 4 with clean background" + source: ["f3s04.wav", "m3s04.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_5: + name: "cat2/a2s05.wav" + description: "Room 4 with clean background" + source: ["m1s04.wav", "f1s04.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_6: + name: "cat2/a2s06.wav" + description: "Room 4 with clean background" + source: ["f2s04.wav", "m2s04.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: Room 4 with clean background" + source: ["m2s13.wav", "f2s13.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_1: + name: "cat3/a3s01.wav" + description: "Room 2 with clean background" + source: ["f2s05.wav", "m2s05.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat3_2: + name: "cat3/a3s02.wav" + description: "Room 2 with clean background" + source: ["m3s05.wav", "f3s05.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat3_3: + name: "cat3/a3s03.wav" + description: "Room 2 with clean background" + source: ["f1s05.wav", "m1s05.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat3_4: + name: "cat3/a3s04.wav" + description: "Room 2 with clean background" + source: ["m2s06.wav", "f2s06.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat3_5: + name: "cat3/a3s05.wav" + description: "Room 2 with clean background" + source: ["f3s06.wav", "m3s06.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat3_6: + name: "cat3/a3s06.wav" + description: "Room 2 with clean background" + source: ["m1s06.wav", "f1s06.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: Room 2 with clean background" + source: ["f3s13.wav", "m3s13.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat4_1: + name: "cat4/a4s01.wav" + description: "Room 5 with clean background" + source: ["m1s07.wav", "f1s07.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_2: + name: "cat4/a4s02.wav" + description: "Room 5 with clean background" + source: ["f2s07.wav", "m2s07.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_3: + name: "cat4/a4s03.wav" + description: "Room 5 with clean background" + source: ["m3s07.wav", "f3s07.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_4: + name: "cat4/a4s04.wav" + description: "Room 5 with clean background" + source: ["f1s08.wav", "m1s08.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_5: + name: "cat4/a4s05.wav" + description: "Room 5 with clean background" + source: ["m2s08.wav", "f2s08.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_6: + name: "cat4/a4s06.wav" + description: "Room 5 with clean background" + source: ["f3s08.wav", "m3s08.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: Room 5 with clean background" + source: ["m1s14.wav", "f1s14.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_1: + name: "cat5/a5s01.wav" + description: "Room 3 with clean background" + source: ["f3s09.wav", "m3s09.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat5_2: + name: "cat5/a5s02.wav" + description: "Room 3 with clean background" + source: ["m1s09.wav", "f1s09.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat5_3: + name: "cat5/a5s03.wav" + description: "Room 3 with clean background" + source: ["f2s09.wav", "m2s09.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat5_4: + name: "cat5/a5s04.wav" + description: "Room 3 with clean background" + source: ["m3s10.wav", "f3s10.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat5_5: + name: "cat5/a5s05.wav" + description: "Room 3 with clean background" + source: ["f1s10.wav", "m1s10.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat5_6: + name: "cat5/a5s06.wav" + description: "Room 3 with clean background" + source: ["m2s10.wav", "f2s10.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: Room 3 with clean background" + source: ["f2s14.wav", "m2s14.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: 1.0 + format: "FOA" + + cat6_1: + name: "cat6/a6s01.wav" + description: "Room 6 with clean background" + source: ["m2s11.wav", "f2s11.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_2: + name: "cat6/a6s02.wav" + description: "Room 6 with clean background" + source: ["f3s11.wav", "m3s11.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_3: + name: "cat6/a6s03.wav" + description: "Room 6 with clean background" + source: ["m1s11.wav", "f1s11.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_4: + name: "cat6/a6s04.wav" + description: "Room 6 with clean background" + source: ["f2s12.wav", "m2s12.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_5: + name: "cat6/a6s05.wav" + description: "Room 6 with clean background" + source: ["m3s12.wav", "f3s12.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_6: + name: "cat6/a6s06.wav" + description: "Room 6 with clean background" + source: ["f1s12.wav", "m1s12.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary: Room 6 with clean background" + source: ["m3s14.wav", "f3s14.wav"] + IR: ["IR_do_p04_e_01_01_FOA.wav", "IR_do_p04_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + diff --git a/experiments/selection/P800-4/config/item_gen_P800-4.yml b/experiments/selection/P800-4/config/item_gen_P800-4_c.yml similarity index 99% rename from experiments/selection/P800-4/config/item_gen_P800-4.yml rename to experiments/selection/P800-4/config/item_gen_P800-4_c.yml index 3aedfdea..dcb3de26 100644 --- a/experiments/selection/P800-4/config/item_gen_P800-4.yml +++ b/experiments/selection/P800-4/config/item_gen_P800-4_c.yml @@ -18,10 +18,10 @@ fs: 48000 # IR_fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-4/gen_input/items_mono" ### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' -IR_path: "./IRs" +IR_path: "experiments/selection/P800-4/gen_input/IRs" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-4/proc_input" @@ -40,7 +40,7 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider -listening_lab: "l" +listening_lab: "c" language: "EN" exp: "p04" provider: "g" diff --git a/experiments/selection/P800-5/config/item_gen_P800-5.yml b/experiments/selection/P800-5/config/item_gen_P800-5_a.yml similarity index 99% rename from experiments/selection/P800-5/config/item_gen_P800-5.yml rename to experiments/selection/P800-5/config/item_gen_P800-5_a.yml index 2ed8d051..2067997e 100644 --- a/experiments/selection/P800-5/config/item_gen_P800-5.yml +++ b/experiments/selection/P800-5/config/item_gen_P800-5_a.yml @@ -18,10 +18,10 @@ fs: 48000 # IR_fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-5/gen_input/items_mono" ### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' -IR_path: "./IRs" +IR_path: "experiments/selection/P800-5/gen_input/IRs" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-5/proc_input" @@ -40,8 +40,8 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider -listening_lab: "l" -language: "EN" +listening_lab: "a" +language: "DA" exp: "p05" provider: "g" diff --git a/experiments/selection/P800-5/config/item_gen_P800-5_b.yml b/experiments/selection/P800-5/config/item_gen_P800-5_b.yml new file mode 100644 index 00000000..01310a14 --- /dev/null +++ b/experiments/selection/P800-5/config/item_gen_P800-5_b.yml @@ -0,0 +1,445 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: "FOA" + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### IR sampling rate in Hz (only for files in .pcm format); default = 48000 +# IR_fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-5/gen_input/items_mono" + +### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' +IR_path: "experiments/selection/P800-5/gen_input/IRs" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-5/proc_input" + +### (Optional) Output path for binauralized versions of the generated FOA items +# binaural_path: "./items_FOA_bin" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider +listening_lab: "b" +language: "GE" +exp: "p05" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all IR filenames (default: "") +### p stands for the 'provider', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +# use_IR_prefix: "IR_pp_eee_" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### IR: filenames(s) of the input IRs (the program will search for it in the IR_path folder) +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### format: input file format ("FOA" or "HOA2") +### Note 1: use brackets [val1, val2, ...] when specifying multiple values + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the input IR files +### The input IR filenames are represented by: +### IR_pp_eee_r_tt_mm_ffffff.wav +### where: +### pp stands for the provider: do (Dolby), no (Nokia), or (Orange), vo (VoiceAge), g (G.191) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### r stands for the room ID: a, b, c, ... +### tt stands for the talker position: 01, 02, ... +### mm stands for the microphone position: 00, 01, 02, ... +### ffffff stands for the format ID: stAB20, stABC20, stAB100, stAB150, stMS, stBin, FOA, HOA2 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "Car environment 1" + source: ["f1s01.wav", "m1s01.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat1_2: + name: "cat1/a1s02.wav" + description: "Car environment 1" + source: ["m2s01.wav", "f2s01.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat1_3: + name: "cat1/a1s03.wav" + description: "Car environment 1" + source: ["f3s01.wav", "m3s01.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat1_4: + name: "cat1/a1s04.wav" + description: "Car environment 1" + source: ["m1s02.wav", "f1s02.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat1_5: + name: "cat1/a1s05.wav" + description: "Car environment 1" + source: ["f2s02.wav", "m2s02.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat1_6: + name: "cat1/a1s06.wav" + description: "Car environment 1" + source: ["m3s02.wav", "f3s02.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: Car environment 1" + source: ["f1s13.wav", "m1s13.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_1: + name: "cat2/a2s01.wav" + description: "Car environment 1" + source: ["m3s03.wav", "f3s03.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_2: + name: "cat2/a2s02.wav" + description: "Car environment 1" + source: ["f1s03.wav", "m1s03.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_3: + name: "cat2/a2s03.wav" + description: "Car environment 1" + source: ["m2s03.wav", "f2s03.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_4: + name: "cat2/a2s04.wav" + description: "Car environment 1" + source: ["f3s04.wav", "m3s04.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_5: + name: "cat2/a2s05.wav" + description: "Car environment 1" + source: ["m1s04.wav", "f1s04.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_6: + name: "cat2/a2s06.wav" + description: "Car environment 1" + source: ["f2s04.wav", "m2s04.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: Car environment 1" + source: ["m2s13.wav", "f2s13.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_1: + name: "cat3/a3s01.wav" + description: "Outdoor environment 1" + source: ["f2s05.wav", "m2s05.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_2: + name: "cat3/a3s02.wav" + description: "Outdoor environment 1" + source: ["m3s05.wav", "f3s05.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_3: + name: "cat3/a3s03.wav" + description: "Outdoor environment 1" + source: ["f1s05.wav", "m1s05.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_4: + name: "cat3/a3s04.wav" + description: "Outdoor environment 1" + source: ["m2s06.wav", "f2s06.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_5: + name: "cat3/a3s05.wav" + description: "Outdoor environment 1" + source: ["f3s06.wav", "m3s06.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_6: + name: "cat3/a3s06.wav" + description: "Outdoor environment 1" + source: ["m1s06.wav", "f1s06.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: Outdoor environment 1" + source: ["f3s13.wav", "m3s13.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_1: + name: "cat4/a4s01.wav" + description: "Outdoor environment 1" + source: ["m1s07.wav", "f1s07.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_2: + name: "cat4/a4s02.wav" + description: "Outdoor environment 1" + source: ["f2s07.wav", "m2s07.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_3: + name: "cat4/a4s03.wav" + description: "Outdoor environment 1" + source: ["m3s07.wav", "f3s07.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_4: + name: "cat4/a4s04.wav" + description: "Outdoor environment 1" + source: ["f1s08.wav", "m1s08.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_5: + name: "cat4/a4s05.wav" + description: "Outdoor environment 1" + source: ["m2s08.wav", "f2s08.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_6: + name: "cat4/a4s06.wav" + description: "Outdoor environment 1" + source: ["f3s08.wav", "m3s08.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: Outdoor environment 1" + source: ["m1s14.wav", "f1s14.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_1: + name: "cat5/a5s01.wav" + description: "Room environment 1" + source: ["f3s09.wav", "m3s09.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_2: + name: "cat5/a5s02.wav" + description: "Room environment 1" + source: ["m1s09.wav", "f1s09.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_3: + name: "cat5/a5s03.wav" + description: "Room environment 1" + source: ["f2s09.wav", "m2s09.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_4: + name: "cat5/a5s04.wav" + description: "Room environment 1" + source: ["m3s10.wav", "f3s10.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_5: + name: "cat5/a5s05.wav" + description: "Room environment 1" + source: ["f1s10.wav", "m1s10.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_6: + name: "cat5/a5s06.wav" + description: "Room environment 1" + source: ["m2s10.wav", "f2s10.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: Room environment 1" + source: ["f2s14.wav", "m2s14.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_1: + name: "cat6/a6s01.wav" + description: "Room environment 1" + source: ["m2s11.wav", "f2s11.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_2: + name: "cat6/a6s02.wav" + description: "Room environment 1" + source: ["f3s11.wav", "m3s11.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_3: + name: "cat6/a6s03.wav" + description: "Room environment 1" + source: ["m1s11.wav", "f1s11.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_4: + name: "cat6/a6s04.wav" + description: "Room environment 1" + source: ["f2s12.wav", "m2s12.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_5: + name: "cat6/a6s05.wav" + description: "Room environment 1" + source: ["m3s12.wav", "f3s12.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_6: + name: "cat6/a6s06.wav" + description: "Room environment 1" + source: ["f1s12.wav", "m1s12.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary: Room environment 1" + source: ["m3s14.wav", "f3s14.wav"] + IR: ["IR_do_p05_e_01_01_FOA.wav", "IR_do_p05_e_02_01_FOA.wav"] + overlap: -1.0 + format: "FOA" + diff --git a/experiments/selection/P800-6/config/item_gen_P800-6_a.yml b/experiments/selection/P800-6/config/item_gen_P800-6_a.yml new file mode 100644 index 00000000..69541042 --- /dev/null +++ b/experiments/selection/P800-6/config/item_gen_P800-6_a.yml @@ -0,0 +1,424 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: "ISM1" + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-6/gen_input/items_mono" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-6/proc_input" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p06" for exp and "g" for provider +listening_lab: "a" +language: "JA" +exp: "p06" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### azimuth: azimuth in the range [-180,180]; positive values point to the left +### elevation: elevation in the range [-90,90]; positive values indicate up +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### Note 1: use brackets [val1, val2, ...] when specifying multiple values +### Note 2: use the "start:step:stop" notation for moving sources, where step will be applied in 20ms frames +### Note 3: we're using right-handed coordinate system with azimuth = 0 pointing from the nose to the screen + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "Talker sitting at a table" + source: ["m1s01.wav", "m1s07.wav"] + azimuth: 0 + elevation: 0 + overlap: -1.0 + + cat1_2: + name: "cat1/a1s02.wav" + description: "Talker sitting at a table" + source: ["f3s02.wav", "f3s08.wav"] + azimuth: 60 + elevation: 0 + overlap: -1.0 + + cat1_3: + name: "cat1/a1s03.wav" + description: "Talker sitting at a table" + source: ["m3s03.wav", "m3s09.wav"] + azimuth: 120 + elevation: 0 + overlap: -1.0 + + cat1_4: + name: "cat1/a1s04.wav" + description: "Talker sitting at a table" + source: ["f2s04.wav", "f2s10.wav"] + azimuth: 180 + elevation: 0 + overlap: -1.0 + + cat1_5: + name: "cat1/a1s05.wav" + description: "Talker sitting at a table" + source: ["m2s05.wav", "m2s11.wav"] + azimuth: 240 + elevation: 0 + overlap: -1.0 + + cat1_6: + name: "cat1/a1s06.wav" + description: "Talker sitting at a table" + source: ["f1s06.wav", "f1s12.wav"] + azimuth: 300 + elevation: 0 + overlap: -1.0 + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: Talker sitting at a table" + source: ["f1s13.wav", "f1s14.wav"] + azimuth: 0 + elevation: 0 + overlap: -1.0 + + cat2_1: + name: "cat2/a2s01.wav" + description: "Standing talker." + source: ["f1s01.wav", "f1s07.wav"] + azimuth: 120 + elevation: 35 + overlap: -1.0 + + cat2_2: + name: "cat2/a2s02.wav" + description: "Standing talker." + source: ["m1s02.wav", "m1s08.wav"] + azimuth: 180 + elevation: 35 + overlap: -1.0 + + cat2_3: + name: "cat2/a2s03.wav" + description: "Standing talker." + source: ["f3s03.wav", "f3s09.wav"] + azimuth: 240 + elevation: 35 + overlap: -1.0 + + cat2_4: + name: "cat2/a2s04.wav" + description: "Standing talker." + source: ["m3s04.wav", "m3s10.wav"] + azimuth: 300 + elevation: 35 + overlap: -1.0 + + cat2_5: + name: "cat2/a2s05.wav" + description: "Standing talker." + source: ["f2s05.wav", "f2s11.wav"] + azimuth: 0 + elevation: 35 + overlap: -1.0 + + cat2_6: + name: "cat2/a2s06.wav" + description: "Standing talker." + source: ["m2s06.wav", "m2s12.wav"] + azimuth: 60 + elevation: 35 + overlap: -1.0 + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: Standing talker." + source: ["m1s13.wav", "m1s14.wav"] + azimuth: 180 + elevation: 35 + overlap: -1.0 + + cat3_1: + name: "cat3/a3s01.wav" + description: "Smaller talker (child) walking around a table." + source: ["m2s01.wav", "m2s07.wav"] + azimuth: "0:1:360" + elevation: 0 + overlap: -1.0 + + cat3_2: + name: "cat3/a3s02.wav" + description: "Smaller talker (child) walking around a table." + source: ["f1s02.wav", "f1s08.wav"] + azimuth: "60:1:60+360" + elevation: 0 + overlap: -1.0 + + cat3_3: + name: "cat3/a3s03.wav" + description: "Smaller talker (child) walking around a table." + source: ["m1s03.wav", "m1s09.wav"] + azimuth: "120:1:120+360" + elevation: 0 + overlap: -1.0 + + cat3_4: + name: "cat3/a3s04.wav" + description: "Smaller talker (child) walking around a table." + source: ["f3s04.wav", "f3s10.wav"] + azimuth: "180:1:180+360" + elevation: 0 + overlap: -1.0 + + cat3_5: + name: "cat3/a3s05.wav" + description: "Smaller talker (child) walking around a table." + source: ["m3s05.wav", "m3s11.wav"] + azimuth: "240:1:240+360" + elevation: 0 + overlap: -1.0 + + cat3_6: + name: "cat3/a3s06.wav" + description: "Smaller talker (child) walking around a table." + source: ["f2s06.wav", "f2s12.wav"] + azimuth: "300:1:300+360" + elevation: 0 + overlap: -1.0 + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: Smaller talker (child) walking around a table." + source: ["f2s13.wav", "f2s14.wav"] + azimuth: "120:1:120+360" + elevation: 0 + overlap: -1.0 + + cat4_1: + name: "cat4/a4s01.wav" + description: "Talker walking around the table." + source: ["f2s01.wav", "f2s07.wav"] + azimuth: "0:-1:-360" + elevation: 35 + overlap: -1.0 + + cat4_2: + name: "cat4/a4s02.wav" + description: "Talker walking around the table." + source: ["m2s02.wav", "m2s08.wav"] + azimuth: "60:-1:60-360" + elevation: 35 + overlap: -1.0 + + cat4_3: + name: "cat4/a4s03.wav" + description: "Talker walking around the table." + source: ["f1s03.wav", "f1s09.wav"] + azimuth: "120:-1:120-360" + elevation: 35 + overlap: -1.0 + + cat4_4: + name: "cat4/a4s04.wav" + description: "Talker walking around the table." + source: ["m1s04.wav", "m1s10.wav"] + azimuth: "180:-1:180-360" + elevation: 35 + overlap: -1.0 + + cat4_5: + name: "cat4/a4s05.wav" + description: "Talker walking around the table." + source: ["f3s05.wav", "f3s11.wav"] + azimuth: "240:-1:240-360" + elevation: 35 + overlap: -1.0 + + cat4_6: + name: "cat4/a4s06.wav" + description: "Talker walking around the table." + source: ["m3s06.wav", "m3s12.wav"] + azimuth: "300:-1:300-360" + elevation: 35 + overlap: -1.0 + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: Talker walking around the table." + source: ["m2s13.wav", "m2s14.wav"] + azimuth: "180:-1:180-360" + elevation: 35 + overlap: -1.0 + + cat5_1: + name: "cat5/a5s01.wav" + description: "Elevation displacement." + source: ["m3s01.wav", "m3s07.wav"] + azimuth: 240 + elevation: "-90:0.5:90" + overlap: -1.0 + + cat5_2: + name: "cat5/a5s02.wav" + description: "Elevation displacement." + source: ["f2s02.wav", "f2s08.wav"] + azimuth: 300 + elevation: 0 + overlap: -1.0 + + cat5_3: + name: "cat5/a5s03.wav" + description: "Elevation displacement." + source: ["m2s03.wav", "m2s09.wav"] + azimuth: 0 + elevation: "-90:0.5:90" + overlap: -1.0 + + cat5_4: + name: "cat5/a5s04.wav" + description: "Elevation displacement." + source: ["f1s04.wav", "f1s10.wav"] + azimuth: 60 + elevation: "-90:0.5:90" + overlap: -1.0 + + cat5_5: + name: "cat5/a5s05.wav" + description: "Elevation displacement." + source: ["m1s05.wav", "m1s11.wav"] + azimuth: 120 + elevation: "-90:0.5:90" + overlap: -1.0 + + cat5_6: + name: "cat5/a5s06.wav" + description: "Elevation displacement." + source: ["f3s06.wav", "f3s12.wav"] + azimuth: 180 + elevation: "-90:0.5:90" + overlap: -1.0 + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: Elevation displacement." + source: ["f3s13.wav", "f3s14.wav"] + azimuth: 120 + elevation: "-90:0.5:90" + overlap: -1.0 + + cat6_1: + name: "cat6/a6s01.wav" + description: "Azimuth and elevation displacement." + source: ["f3s01.wav", "f3s07.wav"] + azimuth: "60:0.5:60+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + + cat6_2: + name: "cat6/a6s02.wav" + description: "Azimuth and elevation displacement." + source: ["m3s02.wav", "m3s08.wav"] + azimuth: "120:0.5:120+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + + cat6_3: + name: "cat6/a6s03.wav" + description: "Azimuth and elevation displacement." + source: ["f2s03.wav", "f2s09.wav"] + azimuth: "180:0.5:180+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + + cat6_4: + name: "cat6/a6s04.wav" + description: "Azimuth and elevation displacement." + source: ["m2s04.wav", "m2s10.wav"] + azimuth: "240:0.5:240+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + + cat6_5: + name: "cat6/a6s05.wav" + description: "Azimuth and elevation displacement." + source: ["f1s05.wav", "f1s11.wav"] + azimuth: "300:0.5:300+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + + cat6_6: + name: "cat6/a6s06.wav" + description: "Azimuth and elevation displacement." + source: ["m1s06.wav", "m1s12.wav"] + azimuth: "0:0.5:0+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary: Azimuth and elevation displacement." + source: ["m3s13.wav", "m3s14.wav"] + azimuth: "0:0.5:0+180" + elevation: "35:-0.2:-35" + overlap: -1.0 + \ No newline at end of file diff --git a/experiments/selection/P800-6/config/item_gen_P800-6.yml b/experiments/selection/P800-6/config/item_gen_P800-6_c.yml similarity index 99% rename from experiments/selection/P800-6/config/item_gen_P800-6.yml rename to experiments/selection/P800-6/config/item_gen_P800-6_c.yml index 1cddf5bc..162f7bb8 100644 --- a/experiments/selection/P800-6/config/item_gen_P800-6.yml +++ b/experiments/selection/P800-6/config/item_gen_P800-6_c.yml @@ -15,7 +15,7 @@ format: "ISM1" fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-6/gen_input/items_mono" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-6/proc_input" @@ -31,7 +31,7 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p06" for exp and "g" for provider -listening_lab: "l" +listening_lab: "c" language: "EN" exp: "p06" provider: "g" diff --git a/experiments/selection/P800-6/gen_input/IRs/.gitkeep b/experiments/selection/P800-6/gen_input/IRs/.gitkeep deleted file mode 100644 index e69de29b..00000000 diff --git a/experiments/selection/P800-7/config/item_gen_P800-7.yml b/experiments/selection/P800-7/config/item_gen_P800-7_a.yml similarity index 99% rename from experiments/selection/P800-7/config/item_gen_P800-7.yml rename to experiments/selection/P800-7/config/item_gen_P800-7_a.yml index 6a5f7a2e..550b5791 100644 --- a/experiments/selection/P800-7/config/item_gen_P800-7.yml +++ b/experiments/selection/P800-7/config/item_gen_P800-7_a.yml @@ -15,7 +15,7 @@ format: "ISM2" fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-7/gen_input/items_mono" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-7/proc_input" @@ -31,8 +31,8 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p07" for exp and "g" for provider -listening_lab: "l" -language: "EN" +listening_lab: "a" +language: "DA" exp: "p07" provider: "g" diff --git a/experiments/selection/P800-7/config/item_gen_P800-7_d.yml b/experiments/selection/P800-7/config/item_gen_P800-7_d.yml new file mode 100644 index 00000000..65567d3b --- /dev/null +++ b/experiments/selection/P800-7/config/item_gen_P800-7_d.yml @@ -0,0 +1,423 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: "ISM2" + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-7/gen_input/items_mono" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-7/proc_input" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p07" for exp and "g" for provider +listening_lab: "d" +language: "MA" +exp: "p07" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### azimuth: azimuth in the range [-180,180]; positive values point to the left +### elevation: elevation in the range [-90,90]; positive values indicate up +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### Note 1: use brackets [val1, val2, ...] when specifying multiple values +### Note 2: use the "start:step:stop" notation for moving sources, where step will be applied in 20ms frames +### Note 3: we're using right-handed coordinate system with azimuth = 0 pointing from the nose to the screen + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["m1s01.wav", "f1s01.wav"] + azimuth: [0, 50] + elevation: [0, 0] + overlap: -1.0 + + cat1_2: + name: "cat1/a1s02.wav" + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["f3s08.wav", "m1s08.wav"] + azimuth: [50, 350] + elevation: [0, 0] + overlap: -1.0 + + cat1_3: + name: "cat1/a1s03.wav" + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["f2s09.wav", "m3s09.wav"] + azimuth: [40, 290] + elevation: [0, 0] + overlap: -1.0 + + cat1_4: + name: "cat1/a1s04.wav" + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["f1s10.wav", "m2s10.wav"] + azimuth: [30, 230] + elevation: [15, 15] + overlap: -1.0 + + cat1_5: + name: "cat1/a1s05.wav" + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["m3s05.wav", "f3s05.wav"] + azimuth: [20, 170] + elevation: [15, 15] + overlap: -1.0 + + cat1_6: + name: "cat1/a1s06.wav" + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["m2s06.wav", "f2s06.wav"] + azimuth: [10, 110] + elevation: [15, 15] + overlap: -1.0 + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["m1s13.wav", "f1s13.wav"] + azimuth: [0, 50] + elevation: [0, 0] + overlap: -1.0 + + cat2_1: + name: "cat2/a2s01.wav" + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["m2s01.wav", "f2s01.wav"] + azimuth: [20, 170] + elevation: [30, 30] + overlap: 1.0 + + cat2_2: + name: "cat2/a2s02.wav" + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["m1s02.wav", "f1s02.wav"] + azimuth: [10, 110] + elevation: [30, 30] + overlap: 1.0 + + cat2_3: + name: "cat2/a2s03.wav" + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f3s09.wav", "m1s09.wav"] + azimuth: [0, 50] + elevation: [30, 30] + overlap: 1.0 + + cat2_4: + name: "cat2/a2s04.wav" + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f2s10.wav", "m3s10.wav"] + azimuth: [50, 350] + elevation: [60, 60] + overlap: 1.0 + + cat2_5: + name: "cat2/a2s05.wav" + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f1s11.wav", "m2s11.wav"] + azimuth: [40, 290] + elevation: [60, 60] + overlap: 1.0 + + cat2_6: + name: "cat2/a2s06.wav" + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["m3s06.wav", "f3s06.wav"] + azimuth: [30, 230] + elevation: [60, 60] + overlap: 1.0 + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f2s13.wav", "m2s13.wav"] + azimuth: [10, 110] + elevation: [30, 30] + overlap: 1.0 + + cat3_1: + name: "cat3/a3s01.wav" + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["m3s01.wav", "f3s01.wav"] + azimuth: [40, 290] + elevation: [0, 60] + overlap: -1.0 + + cat3_2: + name: "cat3/a3s02.wav" + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["m2s02.wav", "f2s02.wav"] + azimuth: [30, 230] + elevation: [0, 60] + overlap: -1.0 + + cat3_3: + name: "cat3/a3s03.wav" + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["m1s03.wav", "f1s03.wav"] + azimuth: [20, 170] + elevation: [0, 60] + overlap: -1.0 + + cat3_4: + name: "cat3/a3s04.wav" + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["f3s10.wav", "m1s10.wav"] + azimuth: [10, 110] + elevation: [0, 60] + overlap: -1.0 + + cat3_5: + name: "cat3/a3s05.wav" + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["f2s11.wav", "m3s11.wav"] + azimuth: [0, 50] + elevation: [0, 60] + overlap: -1.0 + + cat3_6: + name: "cat3/a3s06.wav" + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["f1s12.wav", "m2s12.wav"] + azimuth: [50, 350] + elevation: [0, 60] + overlap: -1.0 + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["m3s13.wav", "f3s13.wav"] + azimuth: [20, 170] + elevation: [0, 60] + overlap: -1.0 + + cat4_1: + name: "cat4/a4s01.wav" + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["f1s07.wav", "m2s07.wav"] + azimuth: [50, "180:1:120 + 360"] + elevation: [0, 60] + overlap: 1.0 + + cat4_2: + name: "cat4/a4s02.wav" + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["m3s02.wav", "f3s02.wav"] + azimuth: [300, "-70:-1:-10 - 360"] + elevation: [0, 60] + overlap: 1.0 + + cat4_3: + name: "cat4/a4s03.wav" + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["m2s03.wav", "f2s03.wav"] + azimuth: [250, "-20:-1:-320"] + elevation: [0, 60] + overlap: 1.0 + + cat4_4: + name: "cat4/a4s04.wav" + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["m1s04.wav", "f1s04.wav"] + azimuth: [200, "30:-1:-270"] + elevation: [0, 60] + overlap: 1.0 + + cat4_5: + name: "cat4/a4s05.wav" + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["f3s11.wav", "m1s11.wav"] + azimuth: [150, "80:1:20 + 360"] + elevation: [0, 60] + overlap: 1.0 + + cat4_6: + name: "cat4/a4s06.wav" + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["f2s12.wav", "m3s12.wav"] + azimuth: [100, "130:1:70 + 360"] + elevation: [0, 60] + overlap: 1.0 + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["f1s14.wav", "m1s14.wav"] + azimuth: [200, "30:-1:-270"] + elevation: [0, 60] + overlap: 1.0 + + cat5_1: + name: "cat5/a5s01.wav" + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["f2s07.wav", "m3s07.wav"] + azimuth: ["80:1:20 + 360", "80:1:20 + 360"] + elevation: [10, 60] + overlap: 1.0 + + cat5_2: + name: "cat5/a5s02.wav" + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["f1s08.wav", "m2s08.wav"] + azimuth: ["130:1:70 + 360", "130:1:70 + 360"] + elevation: [10, 60] + overlap: 1.0 + + cat5_3: + name: "cat5/a5s03.wav" + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m3s03.wav", "f3s03.wav"] + azimuth: ["180:1:120 + 360", "180:1:120 + 360"] + elevation: [10, 60] + overlap: 1.0 + + cat5_4: + name: "cat5/a5s04.wav" + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m2s04.wav", "f2s04.wav"] + azimuth: ["-70:-1:-10 - 360", "-70:-1:-10 - 360"] + elevation: [10, 60] + overlap: 1.0 + + cat5_5: + name: "cat5/a5s05.wav" + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m1s05.wav", "f1s05.wav"] + azimuth: ["-20:-1:-320", "-20:-1:-320"] + elevation: [10, 60] + overlap: 1.0 + + cat5_6: + name: "cat5/a5s06.wav" + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["f3s12.wav", "m1s12.wav"] + azimuth: ["30:-1:-270", "30:-1:-270"] + elevation: [10, 60] + overlap: 1.0 + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m2s14.wav", "f2s14.wav"] + azimuth: ["-20:-1:-320", "-20:-1:-320"] + elevation: [10, 60] + overlap: 1.0 + + cat6_1: + name: "cat6/a6s01.wav" + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["f3s07.wav", "m1s07.wav"] + azimuth: ["60:1:0 + 360", "60:-1:120 - 360"] + elevation: [20, 50] + overlap: -1.0 + + cat6_2: + name: "cat6/a6s02.wav" + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["f2s08.wav", "m3s08.wav"] + azimuth: ["0:1:300", "0:-1:60 - 360"] + elevation: [20, 50] + overlap: -1.0 + + cat6_3: + name: "cat6/a6s03.wav" + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["f1s09.wav", "m2s09.wav"] + azimuth: ["300:1:240 + 360", "300:-1:0"] + elevation: [20, 50] + overlap: -1.0 + + cat6_4: + name: "cat6/a6s04.wav" + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["m3s04.wav", "f3s04.wav"] + azimuth: ["240:1:180 + 360", "240:-1:-60"] + elevation: [20, 50] + overlap: -1.0 + + cat6_5: + name: "cat6/a6s05.wav" + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["m2s05.wav", "f2s05.wav"] + azimuth: ["180:1:120 + 360", "180:-1:-120"] + elevation: [20, 50] + overlap: -1.0 + + cat6_6: + name: "cat6/a6s06.wav" + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["m1s06.wav", "f1s06.wav"] + azimuth: ["120:1:60 + 360", "120:-1:180 - 360"] + elevation: [20, 50] + overlap: -1.0 + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary: Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["f3s14.wav", "m3s14.wav"] + azimuth: ["120:1:60 + 360", "120:-1:180 - 360"] + elevation: [20, 50] + overlap: -1.0 + \ No newline at end of file diff --git a/experiments/selection/P800-7/gen_input/IRs/.gitkeep b/experiments/selection/P800-7/gen_input/IRs/.gitkeep deleted file mode 100644 index e69de29b..00000000 diff --git a/experiments/selection/P800-8/config/item_gen_P800-8.yml b/experiments/selection/P800-8/config/item_gen_P800-8_a.yml similarity index 99% rename from experiments/selection/P800-8/config/item_gen_P800-8.yml rename to experiments/selection/P800-8/config/item_gen_P800-8_a.yml index b13ea5d4..4b73aeb8 100644 --- a/experiments/selection/P800-8/config/item_gen_P800-8.yml +++ b/experiments/selection/P800-8/config/item_gen_P800-8_a.yml @@ -18,10 +18,10 @@ fs: 48000 # IR_fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-8/gen_input/items_mono" ### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' -IR_path: "./IRs" +IR_path: "experiments/selection/P800-8/gen_input/IRs" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-8/proc_input" @@ -40,8 +40,8 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider -listening_lab: "l" -language: "EN" +listening_lab: "a" +language: "DA" exp: "p08" provider: "g" diff --git a/experiments/selection/P800-8/config/item_gen_P800-8_b.yml b/experiments/selection/P800-8/config/item_gen_P800-8_b.yml new file mode 100644 index 00000000..d9edb74f --- /dev/null +++ b/experiments/selection/P800-8/config/item_gen_P800-8_b.yml @@ -0,0 +1,445 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: ["FOA", "HOA2"] + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### IR sampling rate in Hz (only for files in .pcm format); default = 48000 +# IR_fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-8/gen_input/items_mono" + +### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' +IR_path: "experiments/selection/P800-8/gen_input/IRs" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-8/proc_input" + +### (Optional) Output path for binauralized versions of the generated FOA items +# binaural_path: "./items_FOA_bin" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider +listening_lab: "b" +language: "GE" +exp: "p08" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all IR filenames (default: "") +### p stands for the 'provider', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +# use_IR_prefix: "IR_pp_eee_" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### IR: filenames(s) of the input IRs (the program will search for it in the IR_path folder) +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### format: input file format ("FOA" or "HOA2") +### Note 1: use brackets [val1, val2, ...] when specifying multiple values + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the input IR files +### The input IR filenames are represented by: +### IR_pp_eee_r_tt_mm_ffffff.wav +### where: +### pp stands for the provider: do (Dolby), no (Nokia), or (Orange), vo (VoiceAge), g (G.191) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### r stands for the room ID: a, b, c, ... +### tt stands for the talker position: 01, 02, ... +### mm stands for the microphone position: 00, 01, 02, ... +### ffffff stands for the format ID: stAB20, stABC20, stAB100, stAB150, stMS, stBin, FOA, HOA2 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "" + source: ["f1s01.wav", "m1s01.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_2: + name: "cat1/a1s02.wav" + description: "" + source: ["m2s01.wav", "f2s01.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_3: + name: "cat1/a1s03.wav" + description: "" + source: ["f3s01.wav", "m3s01.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_4: + name: "cat1/a1s04.wav" + description: "" + source: ["m1s02.wav", "f1s02.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_5: + name: "cat1/a1s05.wav" + description: "" + source: ["f2s02.wav", "m2s02.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_6: + name: "cat1/a1s06.wav" + description: "" + source: ["m3s02.wav", "f3s02.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: " + source: ["f1s13.wav", "m1s13.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat2_1: + name: "cat2/a2s01.wav" + description: "" + source: ["m3s03.wav", "f3s03.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_2: + name: "cat2/a2s02.wav" + description: "" + source: ["f1s03.wav", "m1s03.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_3: + name: "cat2/a2s03.wav" + description: "" + source: ["m2s03.wav", "f2s03.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_4: + name: "cat2/a2s04.wav" + description: "" + source: ["f3s04.wav", "m3s04.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_5: + name: "cat2/a2s05.wav" + description: "" + source: ["m1s04.wav", "f1s04.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_6: + name: "cat2/a2s06.wav" + description: "" + source: ["f2s04.wav", "m2s04.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: " + source: ["m2s13.wav", "f2s13.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat3_1: + name: "cat3/a3s01.wav" + description: "" + source: ["f2s05.wav", "m2s05.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_2: + name: "cat3/a3s02.wav" + description: "" + source: ["m3s05.wav", "f3s05.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_3: + name: "cat3/a3s03.wav" + description: "" + source: ["f1s05.wav", "m1s05.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_4: + name: "cat3/a3s04.wav" + description: "" + source: ["m2s06.wav", "f2s06.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_5: + name: "cat3/a3s05.wav" + description: "" + source: ["f3s06.wav", "m3s06.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_6: + name: "cat3/a3s06.wav" + description: "" + source: ["m1s06.wav", "f1s06.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: " + source: ["f3s13.wav", "m3s13.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat4_1: + name: "cat4/a4s01.wav" + description: "" + source: ["m1s07.wav", "f1s07.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_2: + name: "cat4/a4s02.wav" + description: "" + source: ["f2s07.wav", "m2s07.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_3: + name: "cat4/a4s03.wav" + description: "" + source: ["m3s07.wav", "f3s07.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_4: + name: "cat4/a4s04.wav" + description: "" + source: ["f1s08.wav", "m1s08.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_5: + name: "cat4/a4s05.wav" + description: "" + source: ["m2s08.wav", "f2s08.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_6: + name: "cat4/a4s06.wav" + description: "" + source: ["f3s08.wav", "m3s08.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: " + source: ["m1s14.wav", "f1s14.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat5_1: + name: "cat5/a5s01.wav" + description: "" + source: ["f3s09.wav", "m3s09.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_2: + name: "cat5/a5s02.wav" + description: "" + source: ["m1s09.wav", "f1s09.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_3: + name: "cat5/a5s03.wav" + description: "" + source: ["f2s09.wav", "m2s09.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_4: + name: "cat5/a5s04.wav" + description: "" + source: ["m3s10.wav", "f3s10.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_5: + name: "cat5/a5s05.wav" + description: "" + source: ["f1s10.wav", "m1s10.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_6: + name: "cat5/a5s06.wav" + description: "" + source: ["m2s10.wav", "f2s10.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: " + source: ["f2s14.wav", "m2s14.wav"] + IR: ["IR_do_p08_e_01_01_FOA.wav", "IR_do_p08_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat6_1: + name: "cat6/a6s01.wav" + description: "" + source: ["m2s11.wav", "f2s11.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_2: + name: "cat6/a6s02.wav" + description: "" + source: ["f3s11.wav", "m3s11.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_3: + name: "cat6/a6s03.wav" + description: "" + source: ["m1s11.wav", "f1s11.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_4: + name: "cat6/a6s04.wav" + description: "" + source: ["f2s12.wav", "m2s12.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_5: + name: "cat6/a6s05.wav" + description: "" + source: ["m3s12.wav", "f3s12.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_6: + name: "cat6/a6s06.wav" + description: "" + source: ["f1s12.wav", "m1s12.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary:" + source: ["m3s14.wav", "f3s14.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + diff --git a/experiments/selection/P800-9/config/item_gen_P800-9.yml b/experiments/selection/P800-9/config/item_gen_P800-9_a.yml similarity index 99% rename from experiments/selection/P800-9/config/item_gen_P800-9.yml rename to experiments/selection/P800-9/config/item_gen_P800-9_a.yml index c46edb17..39cd5f0b 100644 --- a/experiments/selection/P800-9/config/item_gen_P800-9.yml +++ b/experiments/selection/P800-9/config/item_gen_P800-9_a.yml @@ -18,10 +18,10 @@ fs: 48000 # IR_fs: 48000 ### Input path to mono files -input_path: "./items_mono" +input_path: "experiments/selection/P800-9/gen_input/items_mono" ### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' -IR_path: "./IRs" +IR_path: "experiments/selection/P800-9/gen_input/IRs" ### Output path for generated test items and metadata files output_path: "experiments/selection/P800-9/proc_input" @@ -40,8 +40,8 @@ postamble: 1.0 add_low_level_random_noise: true ### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider -listening_lab: "l" -language: "EN" +listening_lab: "a" +language: "JA" exp: "p09" provider: "g" diff --git a/experiments/selection/P800-9/config/item_gen_P800-9_d.yml b/experiments/selection/P800-9/config/item_gen_P800-9_d.yml new file mode 100644 index 00000000..073723ca --- /dev/null +++ b/experiments/selection/P800-9/config/item_gen_P800-9_d.yml @@ -0,0 +1,445 @@ +--- +################################################ +# General configuration +################################################ + +### Any relative paths will be interpreted relative to the working directory the script is called from! +### Usage of absolute paths is recommended. +### Do not use file names with dots "." in them! This is not supported, use "_" instead +### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions + +### Output format +format: ["FOA", "HOA2"] + +### Output sampling rate in Hz; default = 48000 +fs: 48000 + +### IR sampling rate in Hz (only for files in .pcm format); default = 48000 +# IR_fs: 48000 + +### Input path to mono files +input_path: "experiments/selection/P800-9/gen_input/items_mono" + +### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR' +IR_path: "experiments/selection/P800-9/gen_input/IRs" + +### Output path for generated test items and metadata files +output_path: "experiments/selection/P800-9/proc_input" + +### (Optional) Output path for binauralized versions of the generated FOA items +# binaural_path: "./items_FOA_bin" + +### Target loudness in LKFS; default = null (no loudness normalization applied) +loudness: -26 + +### Pre-amble and Post-amble length in seconds (default = 0.0) +preamble: 0.5 +postamble: 1.0 + +### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence) +add_low_level_random_noise: true + +### File designators, default is "l" for listening lab, "EN" for language, "p04" for exp and "g" for provider +listening_lab: "d" +language: "FR" +exp: "p09" +provider: "g" + +### Use prefix for all input filenames (default: "") +### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_input_prefix: "lLLeee" + +### Use prefix for all IR filenames (default: "") +### p stands for the 'provider', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +# use_IR_prefix: "IR_pp_eee_" + +### Use prefix for all output filenames (default: "") +### l stands for the 'listening_lab' designator, e stands for the 'exp' designator (the number of consecutive letters define the length of the field) +use_output_prefix: "leee" + +################################################ +### Scene description +################################################ + +### Each scene must begin by specifying the category in the following format: catN_I where N is the category index and N is the scene index +### Each scene shall de described using the following parameters/properties: +### name: filename of the generated output item (the program will save th generated items in the output_path folder, note: it is possible to use subfolders, e.g. items_stereo/x1_s01.wav) +### description: textual description of the scene +### source: filename(s) of the mono input sources (the program will search for it in the input_path folder) +### IR: filenames(s) of the input IRs (the program will search for it in the IR_path folder) +### overlap: overlap length between two input sources in seconds (negative value creates a gap) +### format: input file format ("FOA" or "HOA2") +### Note 1: use brackets [val1, val2, ...] when specifying multiple values + +### Naming convention for the input mono files +### The input filenames are represented by: +### lLLeeettszz.wav +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### LL stands for the language: JP, FR, GE, MA, DA, EN +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### tt stands for the talker ID: f1, f2, f3, m1, m2, m3 +### s stands for 'sample' and zz is the sample number; 01, ..., 14 + +### Naming convention for the input IR files +### The input IR filenames are represented by: +### IR_pp_eee_r_tt_mm_ffffff.wav +### where: +### pp stands for the provider: do (Dolby), no (Nokia), or (Orange), vo (VoiceAge), g (G.191) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### r stands for the room ID: a, b, c, ... +### tt stands for the talker position: 01, 02, ... +### mm stands for the microphone position: 00, 01, 02, ... +### ffffff stands for the format ID: stAB20, stABC20, stAB100, stAB150, stMS, stBin, FOA, HOA2 + +### Naming convention for the generated output files +### The output filenames are represented by: +### leeeayszz.wav +### The filenames of the accompanying output metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by: +### leeeayszz.met for metadata-assisted spatial audio +### leeeayszz.wav.o.csv for object-based audio +### where: +### l stands for the listening lab designator: a (Force Technology), b (HEAD acoustics), c (MQ University), d (Mesaqin.com) +### eee stands for the experiment designator: p01, p02, p04, p05, p06, p07, p08, p09 +### a stands 'audio' +### y is the per-experiment category according to IVAS-8a: 01, 02, 03, 04, 05, 06 +### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07 (07 is the preliminary sample) +### o stands for the object number; 0, 1, 2, 3 + +scenes: + cat1_1: + name: "cat1/a1s01.wav" + description: "" + source: ["f1s01.wav", "m1s01.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_2: + name: "cat1/a1s02.wav" + description: "" + source: ["m2s01.wav", "f2s01.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_3: + name: "cat1/a1s03.wav" + description: "" + source: ["f3s01.wav", "m3s01.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_4: + name: "cat1/a1s04.wav" + description: "" + source: ["m1s02.wav", "f1s02.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_5: + name: "cat1/a1s05.wav" + description: "" + source: ["f2s02.wav", "m2s02.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_6: + name: "cat1/a1s06.wav" + description: "" + source: ["m3s02.wav", "f3s02.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat1_7: + name: "cat1/a1s07.wav" + description: "Preliminary: " + source: ["f1s13.wav", "m1s13.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat2_1: + name: "cat2/a2s01.wav" + description: "" + source: ["m3s03.wav", "f3s03.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_2: + name: "cat2/a2s02.wav" + description: "" + source: ["f1s03.wav", "m1s03.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_3: + name: "cat2/a2s03.wav" + description: "" + source: ["m2s03.wav", "f2s03.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_4: + name: "cat2/a2s04.wav" + description: "" + source: ["f3s04.wav", "m3s04.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_5: + name: "cat2/a2s05.wav" + description: "" + source: ["m1s04.wav", "f1s04.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_6: + name: "cat2/a2s06.wav" + description: "" + source: ["f2s04.wav", "m2s04.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat2_7: + name: "cat2/a2s07.wav" + description: "Preliminary: " + source: ["m2s13.wav", "f2s13.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat3_1: + name: "cat3/a3s01.wav" + description: "" + source: ["f2s05.wav", "m2s05.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_2: + name: "cat3/a3s02.wav" + description: "" + source: ["m3s05.wav", "f3s05.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_3: + name: "cat3/a3s03.wav" + description: "" + source: ["f1s05.wav", "m1s05.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_4: + name: "cat3/a3s04.wav" + description: "" + source: ["m2s06.wav", "f2s06.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_5: + name: "cat3/a3s05.wav" + description: "" + source: ["f3s06.wav", "m3s06.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_6: + name: "cat3/a3s06.wav" + description: "" + source: ["m1s06.wav", "f1s06.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat3_7: + name: "cat3/a3s07.wav" + description: "Preliminary: " + source: ["f3s13.wav", "m3s13.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat4_1: + name: "cat4/a4s01.wav" + description: "" + source: ["m1s07.wav", "f1s07.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_2: + name: "cat4/a4s02.wav" + description: "" + source: ["f2s07.wav", "m2s07.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_3: + name: "cat4/a4s03.wav" + description: "" + source: ["m3s07.wav", "f3s07.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_4: + name: "cat4/a4s04.wav" + description: "" + source: ["f1s08.wav", "m1s08.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_5: + name: "cat4/a4s05.wav" + description: "" + source: ["m2s08.wav", "f2s08.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_6: + name: "cat4/a4s06.wav" + description: "" + source: ["f3s08.wav", "m3s08.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat4_7: + name: "cat4/a4s07.wav" + description: "Preliminary: " + source: ["m1s14.wav", "f1s14.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat5_1: + name: "cat5/a5s01.wav" + description: "" + source: ["f3s09.wav", "m3s09.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_2: + name: "cat5/a5s02.wav" + description: "" + source: ["m1s09.wav", "f1s09.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_3: + name: "cat5/a5s03.wav" + description: "" + source: ["f2s09.wav", "m2s09.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_4: + name: "cat5/a5s04.wav" + description: "" + source: ["m3s10.wav", "f3s10.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_5: + name: "cat5/a5s05.wav" + description: "" + source: ["f1s10.wav", "m1s10.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_6: + name: "cat5/a5s06.wav" + description: "" + source: ["m2s10.wav", "f2s10.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat5_7: + name: "cat5/a5s07.wav" + description: "Preliminary: " + source: ["f2s14.wav", "m2s14.wav"] + IR: ["IR_do_p09_e_01_01_FOA.wav", "IR_do_p09_e_02_01_FOA.wav"] + overlap: 0.5 + format: "FOA" + + cat6_1: + name: "cat6/a6s01.wav" + description: "" + source: ["m2s11.wav", "f2s11.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_2: + name: "cat6/a6s02.wav" + description: "" + source: ["f3s11.wav", "m3s11.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_3: + name: "cat6/a6s03.wav" + description: "" + source: ["m1s11.wav", "f1s11.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_4: + name: "cat6/a6s04.wav" + description: "" + source: ["f2s12.wav", "m2s12.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_5: + name: "cat6/a6s05.wav" + description: "" + source: ["m3s12.wav", "f3s12.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_6: + name: "cat6/a6s06.wav" + description: "" + source: ["f1s12.wav", "m1s12.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + + cat6_7: + name: "cat6/a6s07.wav" + description: "Preliminary:" + source: ["m3s14.wav", "f3s14.wav"] + IR: ["Nokia_Small_Room3_TalkPos1_EigenOwnHoA2_SinSweep_9chn.wav", "Nokia_Small_Room3_TalkPos2_EigenOwnHoA2_SinSweep_9chn.wav"] + overlap: 0.5 + format: "HOA2" + -- GitLab From d7ea269bd1bae19b800be32a9b76c602a9e24c0d Mon Sep 17 00:00:00 2001 From: Treffehn Date: Fri, 16 Jun 2023 10:07:59 +0200 Subject: [PATCH 6/7] formatting and small comment in readme --- README.md | 5 ++++- ivas_processing_scripts/audiotools/metadata.py | 1 - ivas_processing_scripts/generation/__init__.py | 1 - 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 59e67e65..36434bad 100755 --- a/README.md +++ b/README.md @@ -63,9 +63,12 @@ b (HEAD acoustics), c (MQ University), d (Mesaqin.com), and 'LL' stands for the The impluse responses have to be copied to experiments/selection/P800-{X}/gen_input/IRs. -To generate the items run `python -m ivas_processing_scripts.generation experiments/P800-{X}/config/item_gen_P800-{X}_{l}.yml` from the root folder of the repository. +To generate the items run `python -m ivas_processing_scripts.generation experiments/selection/P800-{X}/config/item_gen_P800-{X}_{l}.yml` from the root folder of the repository. The resulting files can be found in 'experiments/selection/P800-{X}/proc_input' sorted by category. +For P800-3 the input files for the processing are already provided by the listening lab. This means this step can be skipped. +For tests with ISM input format (P800-6 and P800-7) no IRs are needed, only mono sentences + ### Item processing If the tests includes background noise, the corresponding files have to be copied to 'experiments/selection/P800-{X}/background_noise'. diff --git a/ivas_processing_scripts/audiotools/metadata.py b/ivas_processing_scripts/audiotools/metadata.py index af87fe3f..7ea1b5fe 100755 --- a/ivas_processing_scripts/audiotools/metadata.py +++ b/ivas_processing_scripts/audiotools/metadata.py @@ -44,7 +44,6 @@ from ivas_processing_scripts.audiotools.constants import ( DEFAULT_ISM_METADATA, FORMAT_ISM_METADATA_CSV, IVAS_FRAME_LEN_MS, - NUMBER_COLUMNS_ISM_METADATA, ) diff --git a/ivas_processing_scripts/generation/__init__.py b/ivas_processing_scripts/generation/__init__.py index 8ee7c026..53892744 100755 --- a/ivas_processing_scripts/generation/__init__.py +++ b/ivas_processing_scripts/generation/__init__.py @@ -31,7 +31,6 @@ # import logging -import os import yaml -- GitLab From 622870570d37ee3182612641fbc7bbf88a99d065 Mon Sep 17 00:00:00 2001 From: Treffehn Date: Fri, 16 Jun 2023 10:21:54 +0200 Subject: [PATCH 7/7] adjusted changes in ISM configs --- .../P800-6/config/item_gen_P800-6_a.yml | 504 +++++++++--------- .../P800-7/config/item_gen_P800-7_d.yml | 394 +++++++------- 2 files changed, 449 insertions(+), 449 deletions(-) diff --git a/experiments/selection/P800-6/config/item_gen_P800-6_a.yml b/experiments/selection/P800-6/config/item_gen_P800-6_a.yml index 69541042..396e5e22 100644 --- a/experiments/selection/P800-6/config/item_gen_P800-6_a.yml +++ b/experiments/selection/P800-6/config/item_gen_P800-6_a.yml @@ -36,6 +36,7 @@ language: "JA" exp: "p06" provider: "g" + ### Use prefix for all input filenames (default: "") ### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'exp' designator (the number of consecutive letters define the length of the field) use_input_prefix: "lLLeee" @@ -92,333 +93,332 @@ scenes: source: ["m1s01.wav", "m1s07.wav"] azimuth: 0 elevation: 0 - overlap: -1.0 + overlap: -0.5 - cat1_2: + cat1_2: name: "cat1/a1s02.wav" - description: "Talker sitting at a table" - source: ["f3s02.wav", "f3s08.wav"] - azimuth: 60 - elevation: 0 - overlap: -1.0 - - cat1_3: + description: "Standing talker." + source: ["m1s02.wav", "m1s08.wav"] + azimuth: 180 + elevation: 35 + overlap: -0.5 + + cat1_3: name: "cat1/a1s03.wav" - description: "Talker sitting at a table" - source: ["m3s03.wav", "m3s09.wav"] - azimuth: 120 + description: "Smaller talker (child) walking around a table." + source: ["m1s03.wav", "m1s09.wav"] + azimuth: "120:1:120+360" elevation: 0 - overlap: -1.0 + overlap: -0.5 - cat1_4: + cat1_4: name: "cat1/a1s04.wav" - description: "Talker sitting at a table" - source: ["f2s04.wav", "f2s10.wav"] - azimuth: 180 - elevation: 0 - overlap: -1.0 + description: "Talker walking around the table." + source: ["m1s04.wav", "m1s10.wav"] + azimuth: "180:-1:180-360" + elevation: 35 + overlap: -0.5 - cat1_5: + cat1_5: name: "cat1/a1s05.wav" - description: "Talker sitting at a table" - source: ["m2s05.wav", "m2s11.wav"] - azimuth: 240 - elevation: 0 - overlap: -1.0 + description: "Elevation displacement." + source: ["m1s05.wav", "m1s11.wav"] + azimuth: 120 + elevation: "-90:0.3:90" + overlap: -0.5 - cat1_6: + cat1_6: name: "cat1/a1s06.wav" - description: "Talker sitting at a table" - source: ["f1s06.wav", "f1s12.wav"] - azimuth: 300 - elevation: 0 - overlap: -1.0 - - cat1_7: + description: "Azimuth and elevation displacement." + source: ["m1s06.wav", "m1s12.wav"] + azimuth: "0:0.5:0+180" + elevation: "35:-0.2:-35" + overlap: -0.5 + + cat1_7: name: "cat1/a1s07.wav" - description: "Preliminary: Talker sitting at a table" - source: ["f1s13.wav", "f1s14.wav"] - azimuth: 0 - elevation: 0 - overlap: -1.0 + description: "Preliminary: Standing talker." + source: ["m1s13.wav", "m1s14.wav"] + azimuth: 180 + elevation: 35 + overlap: -0.5 - cat2_1: + cat2_1: name: "cat2/a2s01.wav" description: "Standing talker." source: ["f1s01.wav", "f1s07.wav"] azimuth: 120 elevation: 35 - overlap: -1.0 - - cat2_2: + overlap: -0.5 + + cat2_2: name: "cat2/a2s02.wav" - description: "Standing talker." - source: ["m1s02.wav", "m1s08.wav"] - azimuth: 180 - elevation: 35 - overlap: -1.0 - - cat2_3: + description: "Smaller talker (child) walking around a table." + source: ["f1s02.wav", "f1s08.wav"] + azimuth: "60:1:60+360" + elevation: 0 + overlap: -0.5 + + cat2_3: name: "cat2/a2s03.wav" - description: "Standing talker." - source: ["f3s03.wav", "f3s09.wav"] - azimuth: 240 + description: "Talker walking around the table." + source: ["f1s03.wav", "f1s09.wav"] + azimuth: "120:-1:120-360" elevation: 35 - overlap: -1.0 - - cat2_4: + overlap: -0.5 + + cat2_4: name: "cat2/a2s04.wav" - description: "Standing talker." - source: ["m3s04.wav", "m3s10.wav"] - azimuth: 300 - elevation: 35 - overlap: -1.0 + description: "Elevation displacement." + source: ["f1s04.wav", "f1s10.wav"] + azimuth: 60 + elevation: "-90:0.3:90" + overlap: -0.5 - cat2_5: + cat2_5: name: "cat2/a2s05.wav" - description: "Standing talker." - source: ["f2s05.wav", "f2s11.wav"] - azimuth: 0 - elevation: 35 - overlap: -1.0 + description: "Azimuth and elevation displacement." + source: ["f1s05.wav", "f1s11.wav"] + azimuth: "300:0.5:300+180" + elevation: "35:-0.2:-35" + overlap: -0.5 - cat2_6: + cat2_6: name: "cat2/a2s06.wav" - description: "Standing talker." - source: ["m2s06.wav", "m2s12.wav"] - azimuth: 60 - elevation: 35 - overlap: -1.0 - - cat2_7: + description: "Talker sitting at a table" + source: ["f1s06.wav", "f1s12.wav"] + azimuth: 300 + elevation: 0 + overlap: -0.5 + + cat2_7: name: "cat2/a2s07.wav" - description: "Preliminary: Standing talker." - source: ["m1s13.wav", "m1s14.wav"] - azimuth: 180 - elevation: 35 - overlap: -1.0 + description: "Preliminary: Talker sitting at a table" + source: ["f1s13.wav", "f1s14.wav"] + azimuth: 0 + elevation: 0 + overlap: -0.5 - cat3_1: + cat3_1: name: "cat3/a3s01.wav" description: "Smaller talker (child) walking around a table." source: ["m2s01.wav", "m2s07.wav"] azimuth: "0:1:360" elevation: 0 - overlap: -1.0 + overlap: -0.5 - cat3_2: + cat3_2: name: "cat3/a3s02.wav" - description: "Smaller talker (child) walking around a table." - source: ["f1s02.wav", "f1s08.wav"] - azimuth: "60:1:60+360" - elevation: 0 - overlap: -1.0 - - cat3_3: + description: "Talker walking around the table." + source: ["m2s02.wav", "m2s08.wav"] + azimuth: "60:-1:60-360" + elevation: 35 + overlap: -0.5 + + cat3_3: name: "cat3/a3s03.wav" - description: "Smaller talker (child) walking around a table." - source: ["m1s03.wav", "m1s09.wav"] - azimuth: "120:1:120+360" - elevation: 0 - overlap: -1.0 - - cat3_4: + description: "Elevation displacement." + source: ["m2s03.wav", "m2s09.wav"] + azimuth: 0 + elevation: "-90:0.3:90" + overlap: -0.5 + + cat3_4: name: "cat3/a3s04.wav" - description: "Smaller talker (child) walking around a table." - source: ["f3s04.wav", "f3s10.wav"] - azimuth: "180:1:180+360" - elevation: 0 - overlap: -1.0 - - cat3_5: + description: "Azimuth and elevation displacement." + source: ["m2s04.wav", "m2s10.wav"] + azimuth: "240:0.5:240+180" + elevation: "35:-0.2:-35" + overlap: -0.5 + + cat3_5: name: "cat3/a3s05.wav" - description: "Smaller talker (child) walking around a table." - source: ["m3s05.wav", "m3s11.wav"] - azimuth: "240:1:240+360" + description: "Talker sitting at a table" + source: ["m2s05.wav", "m2s11.wav"] + azimuth: 240 elevation: 0 - overlap: -1.0 - - cat3_6: + overlap: -0.5 + + cat3_6: name: "cat3/a3s06.wav" - description: "Smaller talker (child) walking around a table." - source: ["f2s06.wav", "f2s12.wav"] - azimuth: "300:1:300+360" - elevation: 0 - overlap: -1.0 - + description: "Standing talker." + source: ["m2s06.wav", "m2s12.wav"] + azimuth: 60 + elevation: 35 + overlap: -0.5 + cat3_7: name: "cat3/a3s07.wav" - description: "Preliminary: Smaller talker (child) walking around a table." - source: ["f2s13.wav", "f2s14.wav"] - azimuth: "120:1:120+360" - elevation: 0 - overlap: -1.0 - - cat4_1: + description: "Preliminary: Talker walking around the table." + source: ["m2s13.wav", "m2s14.wav"] + azimuth: "180:-1:180-360" + elevation: 35 + overlap: -0.5 + + cat4_1: name: "cat4/a4s01.wav" description: "Talker walking around the table." source: ["f2s01.wav", "f2s07.wav"] azimuth: "0:-1:-360" elevation: 35 - overlap: -1.0 - - cat4_2: + overlap: -0.5 + + cat4_2: name: "cat4/a4s02.wav" - description: "Talker walking around the table." - source: ["m2s02.wav", "m2s08.wav"] - azimuth: "60:-1:60-360" - elevation: 35 - overlap: -1.0 - - cat4_3: + description: "Elevation displacement." + source: ["f2s02.wav", "f2s08.wav"] + azimuth: 300 + elevation: "-90:0.3:90" + overlap: -0.5 + + cat4_3: name: "cat4/a4s03.wav" - description: "Talker walking around the table." - source: ["f1s03.wav", "f1s09.wav"] - azimuth: "120:-1:120-360" - elevation: 35 - overlap: -1.0 - - cat4_4: + description: "Azimuth and elevation displacement." + source: ["f2s03.wav", "f2s09.wav"] + azimuth: "180:0.5:180+180" + elevation: "35:-0.2:-35" + overlap: -0.5 + + cat4_4: name: "cat4/a4s04.wav" - description: "Talker walking around the table." - source: ["m1s04.wav", "m1s10.wav"] - azimuth: "180:-1:180-360" - elevation: 35 - overlap: -1.0 - - cat4_5: + description: "Talker sitting at a table" + source: ["f2s04.wav", "f2s10.wav"] + azimuth: 180 + elevation: 0 + overlap: -0.5 + + cat4_5: name: "cat4/a4s05.wav" - description: "Talker walking around the table." - source: ["f3s05.wav", "f3s11.wav"] - azimuth: "240:-1:240-360" + description: "Standing talker." + source: ["f2s05.wav", "f2s11.wav"] + azimuth: 0 elevation: 35 - overlap: -1.0 - - cat4_6: - name: "cat4/a4s06.wav" - description: "Talker walking around the table." - source: ["m3s06.wav", "m3s12.wav"] - azimuth: "300:-1:300-360" - elevation: 35 - overlap: -1.0 + overlap: -0.5 + cat4_6: + name: "cat4/a4s06.wav" + description: "Smaller talker (child) walking around a table." + source: ["f2s06.wav", "f2s12.wav"] + azimuth: "300:1:300+360" + elevation: 0 + overlap: -0.5 + cat4_7: name: "cat4/a4s07.wav" - description: "Preliminary: Talker walking around the table." - source: ["m2s13.wav", "m2s14.wav"] - azimuth: "180:-1:180-360" - elevation: 35 - overlap: -1.0 - - cat5_1: + description: "Preliminary: Smaller talker (child) walking around a table." + source: ["f2s13.wav", "f2s14.wav"] + azimuth: "120:1:120+360" + elevation: 0 + overlap: -0.5 + + cat5_1: name: "cat5/a5s01.wav" description: "Elevation displacement." source: ["m3s01.wav", "m3s07.wav"] azimuth: 240 - elevation: "-90:0.5:90" - overlap: -1.0 - - cat5_2: + elevation: "-90:0.3:90" + overlap: -0.5 + + cat5_2: name: "cat5/a5s02.wav" - description: "Elevation displacement." - source: ["f2s02.wav", "f2s08.wav"] - azimuth: 300 - elevation: 0 - overlap: -1.0 - - cat5_3: + description: "Azimuth and elevation displacement." + source: ["m3s02.wav", "m3s08.wav"] + azimuth: "120:0.5:120+180" + elevation: "35:-0.2:-35" + overlap: -0.5 + + cat5_3: name: "cat5/a5s03.wav" - description: "Elevation displacement." - source: ["m2s03.wav", "m2s09.wav"] - azimuth: 0 - elevation: "-90:0.5:90" - overlap: -1.0 - - cat5_4: + description: "Talker sitting at a table" + source: ["m3s03.wav", "m3s09.wav"] + azimuth: 120 + elevation: 0 + overlap: -0.5 + + cat5_4: name: "cat5/a5s04.wav" - description: "Elevation displacement." - source: ["f1s04.wav", "f1s10.wav"] - azimuth: 60 - elevation: "-90:0.5:90" - overlap: -1.0 - - cat5_5: + description: "Standing talker." + source: ["m3s04.wav", "m3s10.wav"] + azimuth: 300 + elevation: 35 + overlap: -0.5 + + cat5_5: name: "cat5/a5s05.wav" - description: "Elevation displacement." - source: ["m1s05.wav", "m1s11.wav"] - azimuth: 120 - elevation: "-90:0.5:90" - overlap: -1.0 - - cat5_6: + description: "Smaller talker (child) walking around a table." + source: ["m3s05.wav", "m3s11.wav"] + azimuth: "240:1:240+360" + elevation: 0 + overlap: -0.5 + + cat5_6: name: "cat5/a5s06.wav" - description: "Elevation displacement." - source: ["f3s06.wav", "f3s12.wav"] - azimuth: 180 - elevation: "-90:0.5:90" - overlap: -1.0 - + description: "Talker walking around the table." + source: ["m3s06.wav", "m3s12.wav"] + azimuth: "300:-1:300-360" + elevation: 35 + overlap: -0.5 + cat5_7: name: "cat5/a5s07.wav" - description: "Preliminary: Elevation displacement." - source: ["f3s13.wav", "f3s14.wav"] - azimuth: 120 - elevation: "-90:0.5:90" - overlap: -1.0 - - cat6_1: + description: "Preliminary: Azimuth and elevation displacement." + source: ["m3s13.wav", "m3s14.wav"] + azimuth: "0:0.5:0+180" + elevation: "35:-0.2:-35" + overlap: -0.5 + + cat6_1: name: "cat6/a6s01.wav" description: "Azimuth and elevation displacement." source: ["f3s01.wav", "f3s07.wav"] azimuth: "60:0.5:60+180" elevation: "35:-0.2:-35" - overlap: -1.0 - - cat6_2: + overlap: -0.5 + + cat6_2: name: "cat6/a6s02.wav" - description: "Azimuth and elevation displacement." - source: ["m3s02.wav", "m3s08.wav"] - azimuth: "120:0.5:120+180" - elevation: "35:-0.2:-35" - overlap: -1.0 - - cat6_3: + description: "Talker sitting at a table" + source: ["f3s02.wav", "f3s08.wav"] + azimuth: 60 + elevation: 0 + overlap: -0.5 + + cat6_3: name: "cat6/a6s03.wav" - description: "Azimuth and elevation displacement." - source: ["f2s03.wav", "f2s09.wav"] - azimuth: "180:0.5:180+180" - elevation: "35:-0.2:-35" - overlap: -1.0 - - cat6_4: + description: "Standing talker." + source: ["f3s03.wav", "f3s09.wav"] + azimuth: 240 + elevation: 35 + overlap: -0.5 + + cat6_4: name: "cat6/a6s04.wav" - description: "Azimuth and elevation displacement." - source: ["m2s04.wav", "m2s10.wav"] - azimuth: "240:0.5:240+180" - elevation: "35:-0.2:-35" - overlap: -1.0 - - cat6_5: + description: "Smaller talker (child) walking around a table." + source: ["f3s04.wav", "f3s10.wav"] + azimuth: "180:1:180+360" + elevation: 0 + overlap: -0.5 + + cat6_5: name: "cat6/a6s05.wav" - description: "Azimuth and elevation displacement." - source: ["f1s05.wav", "f1s11.wav"] - azimuth: "300:0.5:300+180" - elevation: "35:-0.2:-35" - overlap: -1.0 - - cat6_6: + description: "Talker walking around the table." + source: ["f3s05.wav", "f3s11.wav"] + azimuth: "240:-1:240-360" + elevation: 35 + overlap: -0.5 + + cat6_6: name: "cat6/a6s06.wav" - description: "Azimuth and elevation displacement." - source: ["m1s06.wav", "m1s12.wav"] - azimuth: "0:0.5:0+180" - elevation: "35:-0.2:-35" - overlap: -1.0 + description: "Elevation displacement." + source: ["f3s06.wav", "f3s12.wav"] + azimuth: 180 + elevation: "-90:0.3:90" + overlap: -0.5 cat6_7: name: "cat6/a6s07.wav" - description: "Preliminary: Azimuth and elevation displacement." - source: ["m3s13.wav", "m3s14.wav"] - azimuth: "0:0.5:0+180" - elevation: "35:-0.2:-35" - overlap: -1.0 - \ No newline at end of file + description: "Preliminary: Elevation displacement." + source: ["f3s13.wav", "f3s14.wav"] + azimuth: 120 + elevation: "-90:0.3:90" + overlap: -0.5 diff --git a/experiments/selection/P800-7/config/item_gen_P800-7_d.yml b/experiments/selection/P800-7/config/item_gen_P800-7_d.yml index 65567d3b..35d89e61 100644 --- a/experiments/selection/P800-7/config/item_gen_P800-7_d.yml +++ b/experiments/selection/P800-7/config/item_gen_P800-7_d.yml @@ -95,106 +95,106 @@ scenes: cat1_2: name: "cat1/a1s02.wav" - description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." - source: ["f3s08.wav", "m1s08.wav"] - azimuth: [50, 350] - elevation: [0, 0] - overlap: -1.0 + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["m1s02.wav", "f1s02.wav"] + azimuth: [10, 110] + elevation: [35, 35] + overlap: 1.0 cat1_3: name: "cat1/a1s03.wav" - description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." - source: ["f2s09.wav", "m3s09.wav"] - azimuth: [40, 290] - elevation: [0, 0] - overlap: -1.0 - + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["m1s03.wav", "f1s03.wav"] + azimuth: [20, 170] + elevation: [0, 45] + overlap: -1.0 + cat1_4: name: "cat1/a1s04.wav" - description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." - source: ["f1s10.wav", "m2s10.wav"] - azimuth: [30, 230] - elevation: [15, 15] - overlap: -1.0 - + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["m1s04.wav", "f1s04.wav"] + azimuth: [200, "30:-1:-270"] + elevation: [0, 45] + overlap: 1.0 + cat1_5: name: "cat1/a1s05.wav" - description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." - source: ["m3s05.wav", "f3s05.wav"] - azimuth: [20, 170] - elevation: [15, 15] - overlap: -1.0 - + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m1s05.wav", "f1s05.wav"] + azimuth: ["-20:-1:-320", "-20:-1:-320"] + elevation: [45, 45] + overlap: 1.0 + cat1_6: name: "cat1/a1s06.wav" - description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." - source: ["m2s06.wav", "f2s06.wav"] - azimuth: [10, 110] - elevation: [15, 15] - overlap: -1.0 - - cat1_7: + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["m1s06.wav", "f1s06.wav"] + azimuth: ["120:1:60 + 360", "120:-1:180 - 360"] + elevation: [30, 30] + overlap: -1.0 + + cat1_7: name: "cat1/a1s07.wav" description: "Preliminary: Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." source: ["m1s13.wav", "f1s13.wav"] azimuth: [0, 50] elevation: [0, 0] overlap: -1.0 - + cat2_1: name: "cat2/a2s01.wav" description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." source: ["m2s01.wav", "f2s01.wav"] azimuth: [20, 170] - elevation: [30, 30] + elevation: [35, 35] overlap: 1.0 - + cat2_2: name: "cat2/a2s02.wav" - description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." - source: ["m1s02.wav", "f1s02.wav"] - azimuth: [10, 110] - elevation: [30, 30] - overlap: 1.0 - + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["m2s02.wav", "f2s02.wav"] + azimuth: [30, 230] + elevation: [0, 45] + overlap: -1.0 + cat2_3: name: "cat2/a2s03.wav" - description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." - source: ["f3s09.wav", "m1s09.wav"] - azimuth: [0, 50] - elevation: [30, 30] - overlap: 1.0 - + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["m2s03.wav", "f2s03.wav"] + azimuth: [250, "-20:-1:-320"] + elevation: [0, 45] + overlap: 1.0 + cat2_4: name: "cat2/a2s04.wav" - description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." - source: ["f2s10.wav", "m3s10.wav"] - azimuth: [50, 350] - elevation: [60, 60] - overlap: 1.0 + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m2s04.wav", "f2s04.wav"] + azimuth: ["-70:-1:-10 - 360", "-70:-1:-10 - 360"] + elevation: [45, 45] + overlap: 1.0 cat2_5: name: "cat2/a2s05.wav" - description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." - source: ["f1s11.wav", "m2s11.wav"] - azimuth: [40, 290] - elevation: [60, 60] - overlap: 1.0 + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["m2s05.wav", "f2s05.wav"] + azimuth: ["180:1:120 + 360", "180:-1:-120"] + elevation: [30, 30] + overlap: -1.0 cat2_6: name: "cat2/a2s06.wav" - description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." - source: ["m3s06.wav", "f3s06.wav"] - azimuth: [30, 230] - elevation: [60, 60] - overlap: 1.0 + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["m2s06.wav", "f2s06.wav"] + azimuth: [10, 110] + elevation: [0, 0] + overlap: -1.0 cat2_7: name: "cat2/a2s07.wav" description: "Preliminary: Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." - source: ["f2s13.wav", "m2s13.wav"] + source: ["m2s13.wav", "f2s13.wav"] azimuth: [10, 110] - elevation: [30, 30] + elevation: [35, 35] overlap: 1.0 cat3_1: @@ -202,49 +202,49 @@ scenes: description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." source: ["m3s01.wav", "f3s01.wav"] azimuth: [40, 290] - elevation: [0, 60] + elevation: [0, 45] overlap: -1.0 cat3_2: name: "cat3/a3s02.wav" - description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." - source: ["m2s02.wav", "f2s02.wav"] - azimuth: [30, 230] - elevation: [0, 60] - overlap: -1.0 - + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["m3s02.wav", "f3s02.wav"] + azimuth: [300, "-70:-1:-10 - 360"] + elevation: [0, 45] + overlap: 1.0 + cat3_3: name: "cat3/a3s03.wav" - description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." - source: ["m1s03.wav", "f1s03.wav"] - azimuth: [20, 170] - elevation: [0, 60] - overlap: -1.0 - + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["m3s03.wav", "f3s03.wav"] + azimuth: ["180:1:120 + 360", "180:1:120 + 360"] + elevation: [45, 45] + overlap: 1.0 + cat3_4: name: "cat3/a3s04.wav" - description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." - source: ["f3s10.wav", "m1s10.wav"] - azimuth: [10, 110] - elevation: [0, 60] - overlap: -1.0 - + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["m3s04.wav", "f3s04.wav"] + azimuth: ["240:1:180 + 360", "240:-1:-60"] + elevation: [30, 30] + overlap: -1.0 + cat3_5: name: "cat3/a3s05.wav" - description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." - source: ["f2s11.wav", "m3s11.wav"] - azimuth: [0, 50] - elevation: [0, 60] - overlap: -1.0 - + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["m3s05.wav", "f3s05.wav"] + azimuth: [20, 170] + elevation: [0, 0] + overlap: -1.0 + cat3_6: name: "cat3/a3s06.wav" - description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." - source: ["f1s12.wav", "m2s12.wav"] - azimuth: [50, 350] - elevation: [0, 60] - overlap: -1.0 - + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["m3s06.wav", "f3s06.wav"] + azimuth: [30, 230] + elevation: [35, 35] + overlap: 1.0 + cat3_7: name: "cat3/a3s07.wav" description: "Preliminary: One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." @@ -252,172 +252,172 @@ scenes: azimuth: [20, 170] elevation: [0, 60] overlap: -1.0 - + cat4_1: name: "cat4/a4s01.wav" description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." source: ["f1s07.wav", "m2s07.wav"] azimuth: [50, "180:1:120 + 360"] - elevation: [0, 60] - overlap: 1.0 - + elevation: [0, 45] + overlap: 1.0 + cat4_2: name: "cat4/a4s02.wav" - description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." - source: ["m3s02.wav", "f3s02.wav"] - azimuth: [300, "-70:-1:-10 - 360"] - elevation: [0, 60] - overlap: 1.0 - + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["f1s08.wav", "m2s08.wav"] + azimuth: ["130:1:70 + 360", "130:1:70 + 360"] + elevation: [45, 45] + overlap: 1.0 + cat4_3: name: "cat4/a4s03.wav" - description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." - source: ["m2s03.wav", "f2s03.wav"] - azimuth: [250, "-20:-1:-320"] - elevation: [0, 60] - overlap: 1.0 - + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["f1s09.wav", "m2s09.wav"] + azimuth: ["300:1:240 + 360", "300:-1:0"] + elevation: [30, 30] + overlap: -1.0 + cat4_4: name: "cat4/a4s04.wav" - description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." - source: ["m1s04.wav", "f1s04.wav"] - azimuth: [200, "30:-1:-270"] - elevation: [0, 60] - overlap: 1.0 - + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["f1s10.wav", "m2s10.wav"] + azimuth: [30, 230] + elevation: [0, 0] + overlap: -1.0 + cat4_5: name: "cat4/a4s05.wav" - description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." - source: ["f3s11.wav", "m1s11.wav"] - azimuth: [150, "80:1:20 + 360"] - elevation: [0, 60] - overlap: 1.0 - + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f1s11.wav", "m2s11.wav"] + azimuth: [40, 290] + elevation: [35, 35] + overlap: 1.0 + cat4_6: name: "cat4/a4s06.wav" - description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." - source: ["f2s12.wav", "m3s12.wav"] - azimuth: [100, "130:1:70 + 360"] + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["f1s12.wav", "m2s12.wav"] + azimuth: [50, 350] elevation: [0, 60] - overlap: 1.0 - + overlap: -1.0 + cat4_7: name: "cat4/a4s07.wav" description: "Preliminary: One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." - source: ["f1s14.wav", "m1s14.wav"] + source: ["f1s14.wav", "m2s14.wav"] azimuth: [200, "30:-1:-270"] - elevation: [0, 60] + elevation: [0, 45] overlap: 1.0 - + cat5_1: name: "cat5/a5s01.wav" description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" source: ["f2s07.wav", "m3s07.wav"] azimuth: ["80:1:20 + 360", "80:1:20 + 360"] - elevation: [10, 60] + elevation: [45, 45] overlap: 1.0 - + cat5_2: name: "cat5/a5s02.wav" - description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" - source: ["f1s08.wav", "m2s08.wav"] - azimuth: ["130:1:70 + 360", "130:1:70 + 360"] - elevation: [10, 60] - overlap: 1.0 - + description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." + source: ["f2s08.wav", "m3s08.wav"] + azimuth: ["0:1:300", "0:-1:60 - 360"] + elevation: [30, 30] + overlap: -1.0 + cat5_3: name: "cat5/a5s03.wav" - description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" - source: ["m3s03.wav", "f3s03.wav"] - azimuth: ["180:1:120 + 360", "180:1:120 + 360"] - elevation: [10, 60] - overlap: 1.0 - + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["f2s09.wav", "m3s09.wav"] + azimuth: [40, 290] + elevation: [0, 0] + overlap: -1.0 + cat5_4: name: "cat5/a5s04.wav" - description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" - source: ["m2s04.wav", "f2s04.wav"] - azimuth: ["-70:-1:-10 - 360", "-70:-1:-10 - 360"] - elevation: [10, 60] - overlap: 1.0 - + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f2s10.wav", "m3s10.wav"] + azimuth: [50, 350] + elevation: [35, 35] + overlap: 1.0 + cat5_5: name: "cat5/a5s05.wav" - description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" - source: ["m1s05.wav", "f1s05.wav"] - azimuth: ["-20:-1:-320", "-20:-1:-320"] - elevation: [10, 60] - overlap: 1.0 - + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["f2s11.wav", "m3s11.wav"] + azimuth: [0, 50] + elevation: [0, 45] + overlap: -1.0 + cat5_6: name: "cat5/a5s06.wav" - description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" - source: ["f3s12.wav", "m1s12.wav"] - azimuth: ["30:-1:-270", "30:-1:-270"] - elevation: [10, 60] - overlap: 1.0 - + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["f2s12.wav", "m3s12.wav"] + azimuth: [100, "130:1:70 + 360"] + elevation: [0, 45] + overlap: 1.0 + cat5_7: name: "cat5/a5s07.wav" description: "Preliminary: Two talkers walking side-by-side around the table, ~30% overlapping utterances" - source: ["m2s14.wav", "f2s14.wav"] + source: ["f2s14.wav", "m3s14.wav"] azimuth: ["-20:-1:-320", "-20:-1:-320"] - elevation: [10, 60] + elevation: [45, 45] overlap: 1.0 - + cat6_1: name: "cat6/a6s01.wav" description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." source: ["f3s07.wav", "m1s07.wav"] azimuth: ["60:1:0 + 360", "60:-1:120 - 360"] - elevation: [20, 50] - overlap: -1.0 - + elevation: [30, 30] + overlap: -1.0 + cat6_2: name: "cat6/a6s02.wav" - description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." - source: ["f2s08.wav", "m3s08.wav"] - azimuth: ["0:1:300", "0:-1:60 - 360"] - elevation: [20, 50] - overlap: -1.0 - + description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances." + source: ["f3s08.wav", "m1s08.wav"] + azimuth: [50, 350] + elevation: [0, 0] + overlap: -1.0 + cat6_3: name: "cat6/a6s03.wav" - description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." - source: ["f1s09.wav", "m2s09.wav"] - azimuth: ["300:1:240 + 360", "300:-1:0"] - elevation: [20, 50] - overlap: -1.0 + description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances." + source: ["f3s09.wav", "m1s09.wav"] + azimuth: [0, 50] + elevation: [35, 35] + overlap: 1.0 cat6_4: name: "cat6/a6s04.wav" - description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." - source: ["m3s04.wav", "f3s04.wav"] - azimuth: ["240:1:180 + 360", "240:-1:-60"] - elevation: [20, 50] - overlap: -1.0 - + description: "One talker sitting at a table, second talker standing beside the table, non-overlapping utterances." + source: ["f3s10.wav", "m1s10.wav"] + azimuth: [10, 110] + elevation: [0, 45] + overlap: -1.0 + cat6_5: name: "cat6/a6s05.wav" - description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." - source: ["m2s05.wav", "f2s05.wav"] - azimuth: ["180:1:120 + 360", "180:-1:-120"] - elevation: [20, 50] - overlap: -1.0 - + description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances." + source: ["f3s11.wav", "m1s11.wav"] + azimuth: [150, "80:1:20 + 360"] + elevation: [0, 45] + overlap: 1.0 + cat6_6: name: "cat6/a6s06.wav" - description: "Two talkers walking around the table in opposite directions, non-overlapping utterances." - source: ["m1s06.wav", "f1s06.wav"] - azimuth: ["120:1:60 + 360", "120:-1:180 - 360"] - elevation: [20, 50] - overlap: -1.0 + description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances" + source: ["f3s12.wav", "m1s12.wav"] + azimuth: ["30:-1:-270", "30:-1:-270"] + elevation: [45, 45] + overlap: 1.0 cat6_7: name: "cat6/a6s07.wav" description: "Preliminary: Two talkers walking around the table in opposite directions, non-overlapping utterances." - source: ["f3s14.wav", "m3s14.wav"] + source: ["f3s14.wav", "m1s14.wav"] azimuth: ["120:1:60 + 360", "120:-1:180 - 360"] - elevation: [20, 50] + elevation: [30, 30] overlap: -1.0 \ No newline at end of file -- GitLab