Commit d86eb631 authored by malenovsky's avatar malenovsky
Browse files

Merge branch... 

Merge branch '51-item-generation-apply-newly-proposed-file-naming-convention-to-input-items-and-irs' into 'main'

Resolve "Item-generation: Apply newly proposed file naming convention to input items and IRs"

See merge request !99
parents 846f684d 5f0e7ca9

item_gen_configs/FOA_CONFIG.yml

deleted100644 → 0
+0 −79
Original line number Diff line number Diff line 
---

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

# General configuration

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



### Output format

format: "FOA"



### Output sampling rate in Hz needed for headerless audio files; default = 48000

fs: 48000



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

IR_fs: 48000



### 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



### Input path to mono files

input_path: "./items_mono"



### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR'

IR_path: "./IR_FOA"



### Output path for generated test items and metadata files

output_path: "./items_FOA"



### Target loudness in LKFS; default = null (no loudness normalization applied)

loudness: -26



### Pre-amble and Post-amble length in seconds (default = 0.0)

preamble: 1.0

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





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

### Scene description

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



### Each scene must start with the sceneN tag

### Specify the mono source filename (the program will search for it in the input_path folder)

### Specify the stereo IR source filename (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 [val1, val2, ...] for multiple sources in a scene

### Note 2: use the "start:step:stop" notation for moving sources, where step will be applied in 20ms frames



scenes:

    a1: 

        name: "G1S1.wav"

        description: "Two speakers sitting in a car."

        source: ["fa1.wav", "ma1.wav"]

        IR: ["AmbiX_036x033y_0.01m.wav", "AmbiX_-70x035y_0.01m.wav"]

        overlap: 1.0

        

    a2: 

        name: "G6S2.wav"

        description: "Two speakers sitting in a car."

        source: ["fa1.wav", "ma1.wav"]

        IR: ["AmbiX_-70x035y_0.01m.wav", "AmbiX_036x033y_0.01m.wav"]

        overlap: 1.0



    a3: 

        name: "G2S1.wav"

        description: "Two speakers sitting in a car."

        source: ["fa1.wav", "ma1.wav"]

        IR: ["AmbiX_000x005y_0.1m.wav", "AmbiX_022x-38y_0.01m.wav"]

        overlap: -1.0

        

    a4: 

        name: "G2S2.wav"

        description: "Two speakers sitting in a car."

        source: ["fa1.wav", "ma1.wav"]

        IR: ["AmbiX_022x-38y_0.01m.wav", "AmbiX_000x005y_0.1m.wav"]

        overlap: -1.0

item_gen_configs/HOA2_CONFIG.yml

deleted100644 → 0
+0 −61
Original line number Diff line number Diff line 
---

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

# General configuration

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



### Output format

format: "HOA2"



### Output sampling rate in Hz needed for headerless audio files; default = 48000

fs: 48000



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

IR_fs: 48000



### 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



### Input path to mono files

input_path: "./items_mono"



### Input path to stereo impulse response files, default = './ivas_processing_scripts/generation/IR'

IR_path: "./IRs"



### Output path for generated test items and metadata files

output_path: "./items_HOA2"



### (Optional) Output path for binauralized versions of the generated HOA2 items

# binaural_path: "./items_HOA2_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





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

### Scene description

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



### Each scene must start with the sceneN tag

### Specify the mono source filename (the program will search for it in the input_path folder)

### Specify the stereo IR source filename (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 [val1, val2, ...] for multiple sources in a scene

### Note 2: use the "start:step:stop" notation for moving sources, where step will be applied in 20ms frames



scenes:

    a1: 

        name: "out.wav"

        description: ""

        source: ["fa1.wav", "ma1.wav"]

        IR: ["IR_HOA2_env1/FreefieldFloor_TalkPos1_EigenHoA2_SinSweep_9chn.wav", "IR_HOA2_env1/FreefieldFloor_TalkPos2_EigenHoA2_SinSweep_9chn.wav"]

        overlap: -0.2

item_gen_configs/ISM1_CONFIG.yml

deleted100644 → 0
+0 −303
Original line number Diff line number Diff line 
---

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

# General configuration

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



### Output format

format: "ISM1"



### Output sampling rate in Hz needed for headerless audio files; default = 48000

fs: 48000



### 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



### Input path to mono files

input_path: "./items_mono"



### Output path for generated test items and metadata files

output_path: "./items_ISM1"



### 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: 0.5



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

add_low_level_random_noise: true





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

### Scene description

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



### Each scene must start with the sceneN tag

### Specify the mono source filename (the program will search for it in the input_path folder)

### Specify azimuth and elevation for each input source

### Note 1: use [val1, val2, ...] for multiple sources in a scene

### 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 azi = 0 pointing from the nose to the screen

### azimuth: float, [-180,180]; positive indicates left

### elevation: float, [-90,90]; positive indicates up

### distance: float, tbd: default: 1

### spread: float, [0,360]; spread in angles from 0 ... 360˚

### gain: float, [0,1]



scenes:

    a1: 

        name: "G1S1.wav"

        description: "Talker sitting at a table"

        source: "test_single.wav"

        azimuth: 0 

        elevation: 0 

        

    a2: 

        name: "G6S2.wav"

        description: "Talker sitting at a table"

        source: "test_single.wav"

        azimuth: 60 

        elevation: 0 

        

    a3: 

        name: "G5S3.wav"

        description: "Talker sitting at a table"

        source: "test_single.wav"

        azimuth: 120 

        elevation: 0 



    a4: 

        name: "G4S4.wav"

        description: "Talker sitting at a table"

        source: "test_single.wav"

        azimuth: 180 

        elevation: 0 



    a5: 

        name: "G3S5.wav"

        description: "Talker sitting at a table"

        source: "test_single.wav"

        azimuth: 240 

        elevation: 0 



    a6: 

        name: "G2S6.wav"

        description: "Talker sitting at a table"

        source: "test_single.wav"

        azimuth: 300 

        elevation: 0 



    b1: 

        name: "G2S1.wav"

        description: "standing talker."

        source: "test_single.wav"

        azimuth: 120 

        elevation: 35 

 

    b2: 

        name: "G1S2.wav"

        description: "standing talker."

        source: "test_single.wav"

        azimuth: 180 

        elevation: 35 

 

    b3: 

        name: "G6S3.wav"

        description: "standing talker."

        source: "test_single.wav"

        azimuth: 240 

        elevation: 35 

 

    b4: 

        name: "G5S4.wav"

        description: "standing talker."

        source: "test_single.wav"

        azimuth: 300 

        elevation: 35 



    b5: 

        name: "G4S5.wav"

        description: "standing talker."

        source: "test_single.wav"

        azimuth: 0 

        elevation: 35 



    b6: 

        name: "G3S6.wav"

        description: "standing talker."

        source: "test_single.wav"

        azimuth: 60 

        elevation: 35 



    c1: 

        name: "G3S1.wav"

        description: "Smaller talker (child) walking around a table."

        source: "test_single.wav"

        azimuth: "0:1:360"

        elevation: 0 



    c2: 

        name: "G2S2.wav"

        description: "Smaller talker (child) walking around a table."

        source: "test_single.wav"

        azimuth: "60:1:60+360" 

        elevation: 0 

  

    c3: 

        name: "G1S3.wav"

        description: "Smaller talker (child) walking around a table."

        source: "test_single.wav"

        azimuth: "120:1:120+360" 

        elevation: 0 

  

    c4: 

        name: "G6S4.wav"

        description: "Smaller talker (child) walking around a table."

        source: "test_single.wav"

        azimuth: "180:1:180+360" 

        elevation: 0 

  

    c5: 

        name: "G5S5.wav"

        description: "Smaller talker (child) walking around a table."

        source: "test_single.wav"

        azimuth: "240:1:240+360"

        elevation: 0 

  

    c6: 

        name: "G4S6.wav"

        description: "Smaller talker (child) walking around a table."

        source: "test_single.wav"

        azimuth: "300:1:300+360" 

        elevation: 0 

 

    d1: 

        name: "G4S1.wav"

        description: "Talker walking around the table."

        source: "test_single.wav"

        azimuth: "0:-1:-360"

        elevation: 35 

        

    d2: 

        name: "G3S2.wav"

        description: "Talker walking around the table."

        source: "test_single.wav"

        azimuth: "60:-1:60-360" 

        elevation: 35 

        

    d3: 

        name: "G2S3.wav"

        description: "Talker walking around the table."

        source: "test_single.wav"

        azimuth: "120:-1:120-360" 

        elevation: 35 

 

    d4: 

        name: "G1S4.wav"

        description: "Talker walking around the table."

        source: "test_single.wav"

        azimuth: "180:-1:180-360" 

        elevation: 35 

 

    d5: 

        name: "G6S5.wav"

        description: "Talker walking around the table."

        source: "test_single.wav"

        azimuth: "240:-1:240-360"

        elevation: 35 

 

    d6: 

        name: "G5S6.wav"

        description: "Talker walking around the table."

        source: "test_single.wav"

        azimuth: "300:-1:300-360" 

        elevation: 35

 

    e1: 

        name: "G5S1.wav"

        description: "Elevation displacement."

        source: "test_single.wav"

        azimuth: 240 

        elevation: "-90:0.5:90" 

 

    e2: 

        name: "G4S2.wav"

        description: "Elevation displacement."

        source: "test_single.wav"

        azimuth: 300 

        elevation: 0 

        

    e3: 

        name: "G3S3.wav"

        description: "Elevation displacement."

        source: "test_single.wav"

        azimuth: 0 

        elevation: "-90:0.5:90"  

  

    e4: 

        name: "G2S4.wav"

        description: "Elevation displacement."

        source: "test_single.wav"

        azimuth: 60 

        elevation: "-90:0.5:90"  

  

    e5: 

        name: "G1S5.wav"

        description: "Elevation displacement."

        source: "test_single.wav"

        azimuth: 120 

        elevation: "-90:0.5:90"  

  

    e6: 

        name: "G6S6.wav"

        description: "Elevation displacement."

        source: "test_single.wav"

        azimuth: 180 

        elevation: "-90:0.5:90"  

 

    f1: 

        name: "G6S1.wav"

        description: "Azimuth and elevation displacement."

        source: "test_single.wav"

        azimuth: "60:0.5:60+180" 

        elevation: "35:-0.2:-35"

 

    f2: 

        name: "G5S2.wav"

        description: "Azimuth and elevation displacement."

        source: "test_single.wav"

        azimuth: "120:0.5:120+180" 

        elevation: "35:-0.2:-35" 

  

    f3: 

        name: "G4S3.wav"

        description: "Azimuth and elevation displacement."

        source: "test_single.wav"

        azimuth: "180:0.5:180+180" 

        elevation: "35:-0.2:-35" 

  

    f4: 

        name: "G3S4.wav"

        description: "Azimuth and elevation displacement."

        source: "test_single.wav"

        azimuth: "240:0.5:240+180" 

        elevation: "35:-0.2:-35"

  

    f5: 

        name: "G2S5.wav"

        description: "Azimuth and elevation displacement."

        source: "test_single.wav"

        azimuth: "300:0.5:300+180" 

        elevation: "35:-0.2:-35" 

  

    f6: 

        name: "G1S6.wav"

        description: "Azimuth and elevation displacement."

        source: "test_single.wav"

        azimuth: "0:0.5:0+180" 

        elevation: "35:-0.2:-35" 

  
 No newline at end of file

item_gen_configs/ISM2_CONFIG.yml

deleted100644 → 0
+0 −339

File deleted.

Preview size limit exceeded, changes collapsed.

item_gen_configs/P800-1.yml

+135 −112

File changed.

Preview size limit exceeded, changes collapsed.