Commit f3c848c2 authored by malenovsky's avatar malenovsky
Browse files

Merge branch '96-missing-support-for-mc-format-in-item-generation-scripts' into 'main' 

Resolve "Missing support for MC format in item generation scripts"

See merge request !188
parents 29c30d78 c7b33450

examples/ITEM_GENERATION_5_1_4.yml

0 → 100644
+177 −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: "5_1_4"

# masa_tc: 1        # applicable only to MASA/OMASA format

# masa_dirs: 1      # applicable only to MASA/OMASA format

# sba_order: 2      # applicable only to OSBA format



### 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



### Apply fade-in and fade-out of X seconds

fade_in_out: 0.5



### Trim the output such that the total duration is X seconds

duration: 8



### 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: "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)

###   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)

###   background:  background noise filename (if used, the 'add_low_level_random_noise' parameter is ignored)

###   background_level:  normalized background noise loudness to X dB LKFS

###

### 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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46



    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46

        

    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46

        

    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46

        

    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46

        

    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46



    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46

         

    "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]

        background: "items_background/Dolby_BG_do_p05_a_01_FOA.wav"

        background_level: -46

ivas_processing_scripts/generation/__init__.py

+11 −0
Original line number Diff line number Diff line
@@ -32,6 +32,10 @@ 


import logging



from ivas_processing_scripts.audiotools.constants import (

    CHANNEL_BASED_AUDIO_ALTNAMES,

    CHANNEL_BASED_AUDIO_FORMATS,

)

from ivas_processing_scripts.constants import (

    LOGGER_DATEFMT,

    LOGGER_FORMAT,
@@ -41,6 +45,7 @@ from ivas_processing_scripts.generation import ( 
    config,

    generate_ismN_items,

    generate_masa_items,

    generate_mc_items,

    generate_omasa_items,

    generate_osba_items,

    generate_sba_items,
@@ -100,5 +105,11 @@ def main(args): 
    elif "OSBA" in cfg.format:

        # generate OSBA items from FOA/HOA2/HOA3 and MONO items according to scene description

        generate_osba_items.generate_osba_items(cfg, logger)

    elif (

        cfg.format in CHANNEL_BASED_AUDIO_FORMATS.keys()

        or cfg.format in CHANNEL_BASED_AUDIO_ALTNAMES.keys()

    ):

        # generate MC items from MONO items according to scene description

        generate_mc_items.generate_mc_items(cfg, logger)



    logger.handlers.clear()

ivas_processing_scripts/generation/generate_mc_items.py

0 → 100644
+485 −0

File added.

Preview size limit exceeded, changes collapsed.