Commit ade4f928 authored by Vladimir Malenovsky's avatar Vladimir Malenovsky
Browse files

examples of scene description files (.yml) for item generation scripts

parent 0774f358

examples/ITEM_GENERATION_3ISM.yml

0 → 100644
+171 −0
Original line number Diff line number Diff line 
---

################################################

# Item generation - 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: "ISM3"

# masa_tc: 2

# masa_dirs: 2

# sba_order: 2



### Output sampling rate in Hz

fs: 48000



### Generate BINAURAL output (_BINAURAL will be appended to the output filename)

binaural_output: true



### Normalize target loudness to X LKFS 

# loudness: -26



### Apply pre-amble and post-amble in X seconds 

preamble: 0.0

postamble: 0.0



### Add low-level random background noise (amplitude +-4) instead of silence; default = false (silence)

add_low_level_random_noise: true



### Process with parallel streams

multiprocessing: False



################################################

### Item generation - Filename conventions

################################################



### 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



### File designators, default is "l" for listening lab, "EN" for language, "p07" for experiment and "g" for company

listening_lab: "l"

language: "EN"

exp: "p01"

provider: "va"



### Insert prefix for all input filenames (default: "")

### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'experiment' 

### the number of consecutive letters define the length of each field

# use_input_prefix: "lLLeee"



### Insert prefix for all output filenames (default: "")

### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'experiment' 

### the number of consecutive letters define the length of each field

# use_output_prefix: "leee"



################################################

### Item generation - Scene description

################################################



### Each scene shall de described using the following parameters/properties:

###   output:      output filename

###   description: textual description of the scene

###   input:       input filename(s)

###   azimuth:     azimuth in the range [-180,180]; positive values point to the left

###   elevation:   elevation in the range [-90,90]; positive values indicate up

###   shift:       time adjustment of the input signal (negative value delays the signal)

###

### Note 0: you can use relative paths in filenames (the program assumes that the root directory is the parent directory of the ivas_processing_scripts subfolder)

### 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





scenes:



    "01": 

        output: "out/VA_3obj_2tlks_music1.wav"

        description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."

        input: ["items_mono/untrimmed/f2s1a_Talker1.wav", "items_mono/untrimmed/m2s10a_Talker2.wav", "items_mono/music/Sc01.wav"]

        azimuth: [20, -40, 45]

        elevation: [0, 0, 70]

        level: [-26, -26, -41]

        shift: [0.0, 0.0, 0.0]

        

    "02":

        output: "out/VA_3obj_2tlks_music2.wav"

        description: "One talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."

        input: ["items_mono/untrimmed/f5s10b_Talker1.wav", "items_mono/untrimmed/m3s2b_Talker2.wav", "items_mono/music/Guitar1.wav"]

        azimuth: [50, "180:1:120 + 360", -120]

        elevation: [0, 45, 70]

        level: [-26, -26, -41]

        shift: [0.0, 0.0, 0.0] 

        

    "03":

        output: "out/VA_3obj_2tlks_music3.wav"

        description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances."

        input: ["items_mono/untrimmed/m1s2b_Talker1.wav", "items_mono/untrimmed/f3s5a_Talker2.wav", "items_mono/music/Track066.wav"]

        azimuth: ["80:1:20 + 360", "80:1:20 + 360", -30]

        elevation: [10, 60, 70]

        level: [-26, -26, -41]

        shift: [0.0, 0.0, 0.0] 



    "04":

        output: "out/VA_3obj_2tlks_music4.wav"

        description: "Two talkers walking around the table in opposite directions, ~30% overlapping utterances."

        input: ["items_mono/untrimmed/m4s12b_Talker1.wav", "items_mono/untrimmed/f1s12b_Talker2.wav", "items_mono/music/Sample02.wav"]

        azimuth: ["60:1:0 + 360", "60:-1:120 - 360", 100]

        elevation: [20, 50, 70]

        level: [-26, -26, -41]

        shift: [0.0, 0.0, 0.0] 

        

    "05":

        output: "out/VA_3obj_3tlks_1.wav"

        description: "Three static talkers, partially overlapping utterances."

        input: ["items_mono/untrimmed/m4s12b_Talker1.wav", "items_mono/untrimmed/f1s12b_Talker2.wav", "items_mono/untrimmed/m3s1a_Talker2.wav"]

        azimuth: [30, -45, 100]

        elevation: [20, 20, 30]

        level: [-26, -26, -26]

        shift: [0.0, 0.0, -2.5] 

        

    "06":

        output: "out/VA_3obj_3tlks_2.wav"

        description: "One walking talker, two static talkers, non-overlapping utterances."

        input: ["items_mono/untrimmed/f2s5a_Talker1.wav", "items_mono/untrimmed/m2s16b_Talker2.wav", "items_mono/untrimmed/m3s8b_Talker2.wav"]

        azimuth: ["-20:0.5:360", 60, -45]

        elevation: [10, 10, 10]

        level: [-26, -26, -26]

        shift: [0.0, 0.0, -3.0] 

        

    "07":

        output: "out/VA_3obj_3tlks_3.wav"

        description: "Two moving talkers, one static talker, partially overlapping utterances."

        input: ["items_mono/untrimmed/f1s16b_Talker2.wav", "items_mono/untrimmed/m4s16a_Talker1.wav", "items_mono/untrimmed/f3s10b_Talker2.wav"]

        azimuth: [-90, "0:1:360", "0:-1:-360"]

        elevation: [0, 30, 30]

        level: [-26, -26, -26]

        shift: [0.0, 0.0, -3.0] 



    "08":

        output: "out/VA_3obj_3tlks_4.wav"

        description: "Three walking talkers, partially overlapping utterances."

        input: ["items_mono/untrimmed/f5s15b_Talker1.wav", "items_mono/untrimmed/m3s1a_Talker2.wav", "items_mono/untrimmed/m2s17b_Talker2.wav"]

        azimuth: ["-90:-1:-360", "-10:1.5:360", "70:1:360"]

        elevation: [0, 20, 0]

        level: [-26, -26, -26]

        shift: [0.0, 0.0, -3.5]

examples/ITEM_GENERATION_FOA.yml

0 → 100644
+154 −0
Original line number Diff line number Diff line 
---

################################################

# Item generation - 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"

# masa_tc: 2

# masa_dirs: 2

# sba_order: 2



### Output sampling rate in Hz

fs: 48000



### Generate BINAURAL output (_BINAURAL will be appended to the output filename)

binaural_output: true



### Normalize target loudness to X LKFS 

loudness: -26



### Apply pre-amble and post-amble in X seconds 

preamble: 0.5

postamble: 1.0



### Add low-level random background noise (amplitude +-4) instead of silence; default = false (silence)

add_low_level_random_noise: False



### Process with parallel streams

multiprocessing: False



################################################

### Item generation - Filename conventions

################################################



### 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



### File designators, default is "l" for listening lab, "EN" for language, "p07" for experiment and "g" for company

listening_lab: "b"

language: "GE"

exp: "p02"

provider: "g"



### Insert prefix for all input filenames (default: "")

### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'experiment' 

### the number of consecutive letters define the length of each field

# use_input_prefix: "lLLeee"



### Insert prefix for all output filenames (default: "")

### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'experiment' 

### the number of consecutive letters define the length of each field

use_output_prefix: "leee"



################################################

### Item generation - Scene description

################################################



### Each scene shall de described using the following parameters/properties:

###   output:      output filename

###   description: textual description of the scene

###   input:       input filename(s)

###   IR:          filenames(s) of the input IRs 

###   azimuth:     azimuth in the range [-180,180]; positive values point to the left

###   elevation:   elevation in the range [-90,90]; positive values indicate up

###   shift:       time adjustment of the input signal (negative value delays the signal)

###

### Note 0: you can use relative paths in filenames (the program assumes that the root directory is the parent directory of the ivas_processing_scripts subfolder)

### 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





scenes:

    "01": 

        output: "out/s01.wav"

        description: "Car with AB microphone pickup, no overlap between the talkers, car noise."

        input: ["items_mono/untrimmed/f1s4b_Talker2.wav", "items_mono/untrimmed/f2s1a_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_01_01_FOA.wav", "IRs/IR_do_p04_e_02_01_FOA.wav"]

        shift: [0.0, -1.0]

        

    "02": 

        output: "out/s02.wav"

        description: "Car with AB microphone pickup, overlap between the talkers, car noise."

        input: ["items_mono/untrimmed/f1s6a_Talker2.wav", "items_mono/untrimmed/f2s3b_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_03_01_FOA.wav", "IRs/IR_do_p04_e_04_01_FOA.wav"]

        shift: [0.0, +1.0]

        

    "03": 

        output: "out/s03.wav"

        description: "Car with AB microphone pickup, no overlap between the talkers, car noise."

        input: ["items_mono/untrimmed/f3s3a_Talker2.wav", "items_mono/untrimmed/f3s10b_Talker2.wav"]

        IR: ["IRs/IR_do_p04_e_05_01_FOA.wav", "IRs/IR_do_p04_e_06_01_FOA.wav"]

        shift: [0.0, -1.0]

        

    "04": 

        output: "out/s04.wav"

        description: "Car with AB microphone pickup, no overlap between the talkers, car noise."

        input: ["items_mono/untrimmed/f2s7b_Talker1.wav", "items_mono/untrimmed/f5s15a_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_07_01_FOA.wav", "IRs/IR_do_p04_e_08_01_FOA.wav"]

        shift: [0.0, -1.0]

        

    "05": 

        output: "out/s05.wav"

        description: "Car with AB microphone pickup, no overlap between the talkers, car noise."

        input: ["items_mono/untrimmed/m2s15a_Talker2.wav", "items_mono/untrimmed/m1s4a_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_07_01_FOA.wav", "IRs/IR_do_p04_e_01_01_FOA.wav"]

        shift: [0.0, -1.0]

        

    "06": 

        output: "out/s06.wav"

        description: "Car with AB microphone pickup, no overlap between the talkers."

        input: ["items_mono/untrimmed/m3s8a_Talker2.wav", "items_mono/untrimmed/m4s13a_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_03_01_FOA.wav", "IRs/IR_do_p04_e_01_01_FOA.wav"]

        shift: [0.0, -1.0]

         

    "07": 

        output: "out/s07.wav"

        description: "Preliminary: Car with AB microphone pickup, no overlap between the talkers."

        input: ["items_mono/untrimmed/f1s20a_Talker2.wav", "items_mono/untrimmed/f5s15b_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_02_01_FOA.wav", "IRs/IR_do_p04_e_07_01_FOA.wav"]

        shift: [0.0, -1.0]

         

    "08": 

        output: "out/s08.wav"

        description: "Car with AB microphone pickup, overlap between the talkers."

        input: ["items_mono/untrimmed/m2s6b_Talker2.wav", "items_mono/untrimmed/f5s14a_Talker1.wav"]

        IR: ["IRs/IR_do_p04_e_08_01_FOA.wav", "IRs/IR_do_p04_e_04_01_FOA.wav"]

        shift: [0.0, +1.0]

examples/ITEM_GENERATION_OMASA.yml

0 → 100644
+170 −0
Original line number Diff line number Diff line 
---

################################################

# Item generation - 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: "OMASA"

masa_tc: 2

masa_dirs: 2

# sba_order: 2



### Output sampling rate in Hz

fs: 48000



### Generate BINAURAL output (_BINAURAL will be appended to the output filename)

binaural_output: true



### Normalize target loudness to X LKFS 

# loudness: -26



### Apply pre-amble and post-amble in X seconds 

preamble: 0.0

postamble: 0.0



### Add low-level random background noise (amplitude +-4) instead of silence; default = false (silence)

add_low_level_random_noise: true



### Process with parallel streams

multiprocessing: False



################################################

### Item generation - Filename conventions

################################################



### 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



### File designators, default is "l" for listening lab, "EN" for language, "p07" for experiment and "g" for company

listening_lab: "l"

language: "EN"

exp: "p01"

provider: "va"



### Insert prefix for all input filenames (default: "")

### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'experiment' 

### the number of consecutive letters define the length of each field

# use_input_prefix: "lLLeee"



### Insert prefix for all output filenames (default: "")

### l stands for the 'listening_lab' designator, L stands for the 'language', e stands for the 'experiment' 

### the number of consecutive letters define the length of each field

# use_output_prefix: "leee"



################################################

### Item generation - Scene description

################################################



### Each scene shall de described using the following parameters/properties:

###   output:      output filename

###   description: textual description of the scene

###   input:       input filename(s)

###   azimuth:     azimuth in the range [-180,180]; positive values point to the left

###   elevation:   elevation in the range [-90,90]; positive values indicate up

###   shift:       time adjustment of the input signal (negative value delays the signal)

###

### Note 0: you can use relative paths in filenames (the program assumes that the root directory is the parent directory of the ivas_processing_scripts subfolder)

### 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



scenes:

    "01": 

        output: "out/VA_3tlks_music.wav"

        description: "Three talkers over music background"

        input: ["items_hoa2/bm7aa1s01.wav", "items_mono/untrimmed/m4s12b_Talker1.wav", "items_mono/untrimmed/f1s6a_Talker2.wav", "items_mono/untrimmed/m3s1a_Talker2.wav"]

        azimuth: [0, 30, -45, 100]

        elevation: [0, 20, 20, 30]

        level: [-36, -26, -26, -26]

        shift: [0.0, 0.0, 0.0, -2.0] 

        

    "02":

        output: "out/VA_3tlks_music.wav"

        description: "Three talkers over music background"

        input: ["items_hoa2/bm7aa1s03.wav", "items_mono/untrimmed/f2s5a_Talker1.wav", "items_mono/untrimmed/f5s10a_Talker1.wav", "items_mono/untrimmed/m3s8b_Talker2.wav"]

        azimuth: [0, "-20:0.5:360", "60:-0.5:-360", 60]

        elevation: [0, 10, 10, 10]

        level: [-46, -26, -26, -26]

        shift: [0.0, 0.0, -2.0, -2.5] 

        

    "03":

        output: "out/VA_3tlks_music.wav"

        description: "Three talkers over music background"

        input: ["items_hoa2/bm7aa1s05.wav", "items_mono/untrimmed/f1s16b_Talker2.wav", "items_mono/untrimmed/m4s16a_Talker1.wav", "items_mono/untrimmed/f3s10b_Talker2.wav"]

        azimuth: [0, -90, "0:1:360", "0:-1:-360"]

        elevation: [0, 0, 30, 30]

        level: [-36, -26, -26, -26]

        shift: [0.0, 0.0, 0.0, -2.6] 



    "04":

        output: "out/VA_3tlks_music.wav"

        description: "Three talkers over music background"

        input: ["items_hoa2/bm7aa1s07.wav", "items_mono/untrimmed/f5s15b_Talker1.wav", "items_mono/untrimmed/m1s7a_Talker1.wav", "items_mono/untrimmed/m1s6b_Talker1.wav"]

        azimuth: [0, "-90:-1:-360", "-10:1.5:360", "70:1:360"]

        elevation: [0, 0, 20, 0]

        level: [-46, -26, -36, -26]

        shift: [0.0, -2.0, 0.0, -3.5] 

        

    "05":

        output: "out/VA_2tlks_1obj_music.wav"

        description: "Two talkers, one musical object over music background"

        input: ["items_hoa2/bm7aa1s09.wav", "items_mono/untrimmed/f2s1a_Talker1.wav", "items_mono/untrimmed/f2s5a_Talker1.wav", "music/item_lxa3s3.48k.wav"]

        azimuth: [0, 20, -40, 45]

        elevation: [0, 0, 0, 70]

        level: [-36, -36, -26, -41]

        shift: [0.0, 0.0, -2.0, 0.0]

        

    "06":

        output: "out/VA_2tlks_1obj_music.wav"

        description: "Two talkers, one musical object over music background"

        input: ["items_hoa2/bm7aa1s11.wav", "items_mono/untrimmed/f5s10b_Talker1.wav", "items_mono/untrimmed/m1s4a_Talker1.wav", "music/item_lxa3s5.48k.wav"]

        azimuth: [0, 50, "180:1:360", -120]

        elevation: [0, 0, 45, 70]

        level: [-46, -26, -26, -41]

        shift: [0.0, 0.0, -2.5, 0.0] 

        

    "07":

        output: "out/VA_2tlks_1obj_music.wav"

        description: "Two talkers, one musical object over music background"

        input: ["items_hoa2/bm7aa1s13.wav", "items_mono/untrimmed/m1s2b_Talker1.wav", "items_mono/untrimmed/f3s5a_Talker2.wav", "music/641692__theflyfishingfilmmaker__classical-violin-minor-10s-mono.wav"]

        azimuth: [0, "80:1:20 + 360", "80:1:20 + 360", -30]

        elevation: [0, 10, 60, 70]

        level: [-36, -26, -26, -36]

        shift: [0.0, 0.0, 0.0, 0.0] 



    "08":

        output: "out/VA_2tlks_1obj_music.wav"

        description: "Two talkers, one musical object over music background"

        input: ["items_hoa2/bm7aa1s15.wav", "items_mono/untrimmed/m4s16a_Talker1.wav", "items_mono/untrimmed/f2s4a_Talker1.wav", "music/item_lxa4s2.48k.wav"]

        azimuth: [0, "60:1:0 + 360", "60:-1:120 - 360", 100]

        elevation: [0, 20, 50, 70]

        level: [-46, -26, -26, -41]

        shift: [0.0, 0.0, -1.0, -0.5]

examples/ITEM_GENERATION_OSBA.yml

0 → 100644
+170 −0

File added.

Preview size limit exceeded, changes collapsed.

examples/ITEM_GENERATION_STEREO.yml

0 → 100644
+154 −0

File added.

Preview size limit exceeded, changes collapsed.