naming convention in P800-2.yml (a8a80dc0) · Commits · IVAS Codec Public Collaboration / IVAS Processing Scripts

item_gen_configs/P800-2.yml

+127 −103

Original line number	Diff line number	Diff line
		@@ -3,19 +3,19 @@
		# 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 needed for headerless audio files; default = 48000
		### Output sampling rate in Hz; default = 48000
		fs: 48000

		### IR sampling rate in Hz needed for headerless audio files; default = 48000
		IR_fs: 32000

		### 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
		### IR sampling rate in Hz (only for files in .pcm format); default = 48000
		# IR_fs: 48000

		### Input path to mono files
		input_path: "./items_mono"
		@@ -36,300 +36,324 @@ 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
		listening_lab: "b"
		language: "GE"
		### File designators, default is "l" for listening lab, "EN" for language, "p02" for exp and "g" for provider
		listening_lab: "l"
		language: "EN"
		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"

		################################################
		### Input files
		################################################

		### <LL><Lang><Exp><TalkerID>s<Sample>.wav
		###
		### With
		###
		### <LL> = a (Force Technology), b (HEAD acoustics),
		### c (MQ University), d (Mesaqin.com)
		### <Lang> = JP, FR, GE, MA, DA, EN
		### <Exp> = p01, p02, p04, p05, p06, p07, p08, p09
		### <TalkerID> = f1, f2, f3, m1, m2, m3
		### <Sample> = 01, …, 14

		################################################
		### Scene description
		################################################

		### Each scene must have a unique name
		### Specify the mono source filenames (the program will search for it in the input_path folder)
		### Specify the stereo IR source filenames (the program will search for it in the input_path_IR folder)
		### Specify the overlap length in seconds for each input source (negative value creates a gap)
		### Note 1: use brackets [val1, val2, ...] for multiple sources in a scene
		### Note 2: use the Matlab notation "start:step:stop" to create moving sources (step will be applied in 20ms frames)

		### Naming convention for P.800 items
		### The filenames of the input content samples are represented by:
		### 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 metadata files (applicable to metadata-assisted spatial audio, object-based audio) are represented by:
		### 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 through d according to Table 2)
		### eee stands for the experiment designator, e.g. p01 (see Table 1)
		### a stands audio, and y is the per experiment category according to IVAS-8a
		### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07, where 07 is the preliminary
		### o stands for object number; 0, 1, 2, 3
		### 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: "a1s01"
		name: "cat1/a1s01"
		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: "a1s02"
		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: "a1s03"
		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: "a1s04"
		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: "a1s05"
		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: "a1s06"
		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

		cat2_1:
		name: "a2s01"
		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: "a2s02"
		description: "Car with AB microphone pickup, no overlap between the talkers, street noise."
		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: "a2s03"
		description: "Car with AB microphone pickup, no overlap between the talkers, street noise."
		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: "a2s04"
		description: "Car with AB microphone pickup, no overlap between the talkers, street noise."
		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: "a2s05"
		description: "Car with AB microphone pickup, no overlap between the talkers, street noise."
		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: "a2s06"
		description: "Car with AB microphone pickup, no overlap between the talkers, street noise."
		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

		cat3_1:
		name: "a3s01"
		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: ["SEMSP01.wav", "SEMSP07.wav"]
		IR: ["IR_g_p02_b_01_00_stMS100.wav", "IR_g_p02_b_07_00_stMS100.wav"]
		overlap: -1.0

		cat3_2:
		name: "a3s02"
		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: ["SEMSP05.wav", "SEMSP03.wav"]
		IR: ["IR_g_p02_b_05_00_stMS100.wav", "IR_g_p02_b_03_00_stMS100.wav"]
		overlap: -1.0

		cat3_3:
		name: "a3s03"
		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: ["SEMSP02.wav", "SEMSP06.wav"]
		IR: ["IR_g_p02_b_02_00_stMS100.wav", "IR_g_p02_b_06_00_stMS100.wav"]
		overlap: -1.0

		cat3_4:
		name: "a3s04"
		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: ["SEMSP04.wav", "SEMSP01.wav"]
		IR: ["IR_g_p02_b_04_00_stMS100.wav", "IR_g_p02_b_01_00_stMS100.wav"]
		overlap: -1.0

		cat3_5:
		name: "a3s05"
		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: ["SEMSP03.wav", "SEMSP04.wav"]
		IR: ["IR_g_p02_b_03_00_stMS100.wav", "IR_g_p02_b_04_00_stMS100.wav"]
		overlap: -1.0

		cat3_6:
		name: "a3s06"
		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: ["SEMSP07.wav", "SEMSP02.wav"]
		IR: ["IR_g_p02_b_07_00_stMS100.wav", "IR_g_p02_b_02_00_stMS100.wav"]
		overlap: -1.0

		cat4_1:
		name: "a4s01"
		name: "cat4/a4s01.wav"
		description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["m1s07.wav", "f1s07.wav"]
		IR: ["SEABP01.wav", "SEABP07.wav"]
		IR: ["IR_g_p02_b_01_00_stAB100.wav", "IR_g_p02_b_07_00_stAB100.wav"]
		overlap: -1.0

		cat4_2:
		name: "a4s02"
		name: "cat4/a4s02.wav"
		description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["f2s07.wav", "m2s07.wav"]
		IR: ["SEABP05.wav", "SEABP03.wav"]
		IR: ["IR_g_p02_b_05_00_stAB100.wav", "IR_g_p02_b_03_00_stAB100.wav"]
		overlap: -1.0

		cat4_3:
		name: "a4s03"
		name: "cat4/a4s03.wav"
		description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["m3s07.wav", "f3s07.wav"]
		IR: ["SEABP02.wav", "SEABP06.wav"]
		IR: ["IR_g_p02_b_02_00_stAB100.wav", "IR_g_p02_b_06_00_stAB100.wav"]
		overlap: -1.0

		cat4_4:
		name: "a4s04"
		name: "cat4/a4s04.wav"
		description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["f1s08.wav", "m1s08.wav"]
		IR: ["SEABP04.wav", "SEABP01.wav"]
		IR: ["IR_g_p02_b_04_00_stAB100.wav", "IR_g_p02_b_01_00_stAB100.wav"]
		overlap: -1.0

		cat4_5:
		name: "a4s05"
		name: "cat4/a4s05.wav"
		description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["m2s08.wav", "f2s08.wav"]
		IR: ["SEABP03.wav", "SEABP04.wav"]
		IR: ["IR_g_p02_b_03_00_stAB100.wav", "IR_g_p02_b_04_00_stAB100.wav"]
		overlap: -1.0

		cat4_6:
		name: "a4s06"
		name: "cat4/a4s06.wav"
		description: "Small echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["f3s08.wav", "m3s08.wav"]
		IR: ["SEABP07.wav", "SEABP02.wav"]
		IR: ["IR_g_p02_b_07_00_stAB100.wav", "IR_g_p02_b_02_00_stAB100.wav"]
		overlap: -1.0

		cat5_1:
		name: "a5s01"
		name: "cat5/a5s01.wav"
		description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["f3s09.wav", "m3s09.wav"]
		IR: ["LEABP02.wav", "LEABP08.wav"]
		IR: ["IR_g_p02_d_02_00_stAB150.wav", "IR_g_p02_d_08_00_stAB150.wav"]
		overlap: -1.0

		cat5_2:
		name: "a5s02"
		name: "cat5/a5s02.wav"
		description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["m1s09.wav", "f1s09.wav"]
		IR: ["LEABP09.wav", "LEABP04.wav"]
		IR: ["IR_g_p02_d_09_00_stAB150.wav", "IR_g_p02_d_04_00_stAB150.wav"]
		overlap: -1.0

		cat5_3:
		name: "a5s03"
		name: "cat5/a5s03.wav"
		description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["f2s09.wav", "m2s09.wav"]
		IR: ["LEABP06.wav", "LEABP10.wav"]
		IR: ["IR_g_p02_d_06_00_stAB150.wav", "IR_g_p02_d_10_00_stAB150.wav"]
		overlap: -1.0

		cat5_4:
		name: "a5s04"
		name: "cat5/a5s04.wav"
		description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["m3s10.wav", "f3s10.wav"]
		IR: ["LEABP11.wav", "LEABP08.wav"]
		IR: ["IR_g_p02_d_11_00_stAB150.wav", "IR_g_p02_d_08_00_stAB150.wav"]
		overlap: -1.0

		cat5_5:
		name: "a5s05"
		name: "cat5/a5s05.wav"
		description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["f1s10.wav", "m1s10.wav"]
		IR: ["LEABP10.wav", "LEABP12.wav"]
		IR: ["IR_g_p02_d_10_00_stAB150.wav", "IR_g_p02_d_12_00_stAB150.wav"]
		overlap: -1.0

		cat5_6:
		name: "a5s06"
		name: "cat5/a5s06.wav"
		description: "Large echoic room with AB microphone pickup, partial overlap between the talkers, office noise."
		source: ["m2s10.wav", "f2s10.wav"]
		IR: ["LEABP12.wav", "LEABP01.wav"]
		IR: ["IR_g_p02_d_12_00_stAB150.wav", "IR_g_p02_d_01_00_stAB150.wav"]
		overlap: -1.0

		cat6_1:
		name: "a6s01"
		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: ["SEBIP01.wav", "SEBIP07.wav"]
		IR: ["IR_g_p02_b_01_00_stBI100.wav", "IR_g_p02_b_07_00_stBI100.wav"]
		overlap: -1.0

		cat6_2:
		name: "a6s02"
		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: ["SEBIP05.wav", "SEBIP03.wav"]
		IR: ["IR_g_p02_b_05_00_stBI100.wav", "IR_g_p02_b_03_00_stBI100.wav"]
		overlap: -1.0

		cat6_3:
		name: "a6s03"
		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: ["SEBIP02.wav", "SEBIP06.wav"]
		IR: ["IR_g_p02_b_02_00_stBI100.wav", "IR_g_p02_b_06_00_stBI100.wav"]
		overlap: -1.0

		cat6_4:
		name: "a6s04"
		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: ["SEBIP04.wav", "SEBIP01.wav"]
		IR: ["IR_g_p02_b_04_00_stBI100.wav", "IR_g_p02_b_01_00_stBI100.wav"]
		overlap: -1.0

		cat6_5:
		name: "a6s05"
		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: ["SEBIP03.wav", "SEBIP04.wav"]
		IR: ["IR_g_p02_b_03_00_stBI100.wav", "IR_g_p02_b_04_00_stBI100.wav"]
		overlap: -1.0

		cat6_6:
		name: "a6s06"
		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: ["SEBIP07.wav", "SEBIP02.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