fix extra CRLF in .csv files on Windows (9db60d12) · Commits · IVAS Codec Public Collaboration / IVAS Processing Scripts

item_generation_scripts/config/ISM1_CONFIG.yml

+1 −1

Original line number	Diff line number	Diff line
		@@ -189,7 +189,7 @@ scenes:
		elevation: 35

		d3:
		name: "G3S2.wav"
		name: "G2S3.wav"
		description: "Talker walking around the table."
		source: "test_single.wav"
		azimuth: "120:-1:120-360"

item_generation_scripts/config/ISM2_CONFIG.yml

+36 −36

Original line number	Diff line number	Diff line
		@@ -55,7 +55,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [0, 50]
		elevation: [0, 0]
		delay: [0, 1]
		delay: [0, 0]

		a2:
		name: "G6S2.wav"
		@@ -63,7 +63,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [50, 350]
		elevation: [0, 0]
		delay: [0, 1]
		delay: [0, 0]

		a3:
		name: "G5S3.wav"
		@@ -71,7 +71,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [40, 290]
		elevation: [0, 0]
		delay: [0, 1]
		delay: [0, 0]

		a4:
		name: "G4S4.wav"
		@@ -79,7 +79,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [30, 230]
		elevation: [15, 15]
		delay: [0, 1]
		delay: [0, 0]

		a5:
		name: "G3S5.wav"
		@@ -87,7 +87,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [20, 170]
		elevation: [15, 15]
		delay: [0, 1]
		delay: [0, 0]

		a6:
		name: "G2S6.wav"
		@@ -95,7 +95,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [10, 110]
		elevation: [15, 15]
		delay: [0, 1]
		delay: [0, 0]

		b1:
		name: "G2S1.wav"
		@@ -103,7 +103,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [20, 170]
		elevation: [30, 30]
		delay: [0, 1]
		delay: [0, 1.5]

		b2:
		name: "G1S2.wav"
		@@ -111,7 +111,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [10, 110]
		elevation: [30, 30]
		delay: [0, 1]
		delay: [0, 1.5]

		b3:
		name: "G6S3.wav"
		@@ -119,7 +119,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [0, 50]
		elevation: [30, 30]
		delay: [0, 1]
		delay: [0, 1.5]

		b4:
		name: "G5S4.wav"
		@@ -127,7 +127,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [50, 350]
		elevation: [60, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		b5:
		name: "G4S5.wav"
		@@ -135,7 +135,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [40, 290]
		elevation: [60, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		b6:
		name: "G3S6.wav"
		@@ -143,7 +143,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [30, 230]
		elevation: [60, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		c1:
		name: "G3S1.wav"
		@@ -151,7 +151,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [40, 290]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 0]

		c2:
		name: "G2S2.wav"
		@@ -159,7 +159,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [30, 230]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 0]

		c3:
		name: "G1S3.wav"
		@@ -167,7 +167,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [20, 170]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 0]

		c4:
		name: "G6S4.wav"
		@@ -183,7 +183,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [0, 50]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 0]

		c6:
		name: "G4S6.wav"
		@@ -191,7 +191,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [50, 350]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 0]

		d1:
		name: "G4S1.wav"
		@@ -199,7 +199,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [50, "180:1:120 + 360"]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		d2:
		name: "G3S2.wav"
		@@ -207,15 +207,15 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [300, "-70:-1:-10 - 360"]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		d3:
		name: "G3S2.wav"
		name: "G2S3.wav"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [250, "-20:-1:-320"]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		d4:
		name: "G1S4.wav"
		@@ -223,7 +223,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [200, "30:-1:-270"]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		d5:
		name: "G6S5.wav"
		@@ -231,7 +231,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [150, "80:1:20 + 360"]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		d6:
		name: "G5S6.wav"
		@@ -239,7 +239,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: [100, "130:1:70 + 360"]
		elevation: [0, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		e1:
		name: "G5S1.wav"
		@@ -247,7 +247,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["80:1:20 + 360", "80:1:20 + 360"]
		elevation: [10, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		e2:
		name: "G4S2.wav"
		@@ -255,7 +255,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["130:1:70 + 360", "130:1:70 + 360"]
		elevation: [10, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		e3:
		name: "G3S3.wav"
		@@ -263,7 +263,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["180:1:120 + 360", "180:1:120 + 360"]
		elevation: [10, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		e4:
		name: "G2S4.wav"
		@@ -271,7 +271,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["-70:-1:-10 - 360", "-70:-1:-10 - 360"]
		elevation: [10, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		e5:
		name: "G1S5.wav"
		@@ -279,7 +279,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["-20:-1:-320", "-20:-1:-320"]
		elevation: [10, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		e6:
		name: "G6S6.wav"
		@@ -287,7 +287,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["30:-1:-270", "30:-1:-270"]
		elevation: [10, 60]
		delay: [0, 1]
		delay: [0, 1.5]

		f1:
		name: "G6S1.wav"
		@@ -295,7 +295,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["60:1:0 + 360", "60:-1:120 - 360"]
		elevation: [20, 50]
		delay: [0, 1]
		delay: [0, 0]

		f2:
		name: "G5S2.wav"
		@@ -303,7 +303,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["0:1:300", "0:-1:60 - 360"]
		elevation: [20, 50]
		delay: [0, 1]
		delay: [0, 0]

		f3:
		name: "G4S3.wav"
		@@ -311,7 +311,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["300:1:240 + 360", "300:-1:0"]
		elevation: [20, 50]
		delay: [0, 1]
		delay: [0, 0]

		f4:
		name: "G3S4.wav"
		@@ -319,7 +319,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["240:1:180 + 360", "240:-1:-60"]
		elevation: [20, 50]
		delay: [0, 1]
		delay: [0, 0]

		f5:
		name: "G2S5.wav"
		@@ -327,7 +327,7 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["180:1:120 + 360", "180:-1:-120"]
		elevation: [20, 50]
		delay: [0, 1]
		delay: [0, 0]

		f6:
		name: "G1S6.wav"
		@@ -335,5 +335,5 @@ scenes:
		source: ["test_double.wav", "test_double.wav"]
		azimuth: ["120:1:60 + 360", "120:-1:180 - 360"]
		elevation: [20, 50]
		delay: [0, 1]
		delay: [0, 0]

		No newline at end of file

item_generation_scripts/config/STEREO_CONFIG.yml

0 → 100644

+306 −0

Original line number	Diff line number	Diff line
		---
		################################################
		# General configuration
		################################################

		### Output format
		format: "STEREO"

		### Date; default = YYYYMMDD_HH.MM.SS
		# date: 2023.06.30

		### Deletion of temporary directories containing intermediate processing files, bitstreams etc.; default = false
		# delete_tmp: true

		### 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"

		### Input path to stereo impulse response files
		input_path_IR: "./IR"

		### Output path for generated test items and metadata files
		output_path: "./output"

		### Target loudness in LKFS; default = null (no loudness normalization applied)
		loudness: -26


		################################################
		### 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
		### Specify the delay in seconds 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: "Large anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["LAABP01.L.IR32", "LAABP01.R.IR32"]
		delay: [0, 0]

		a2:
		name: "G6S2.wav"
		description: "Large anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["LAABP02.L.IR32", "LAABP02.R.IR32"]
		delay: [0, 0]

		a3:
		name: "G5S3.wav"
		description: "Large anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["LAABP03.L.IR32", "LAABP03.R.IR32"]
		delay: [0, 0]

		a4:
		name: "G4S4.wav"
		description: "Large anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["LAABP04.L.IR32", "LAABP04.R.IR32"]
		delay: [0, 0]

		a5:
		name: "G3S5.wav"
		description: "Large anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["LAABP05.L.IR32", "LAABP05.R.IR32"]
		delay: [0, 0]

		a6:
		name: "G2S6.wav"
		description: "Large anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["LAABP06.L.IR32", "LAABP06.R.IR32"]
		delay: [0, 0]

		b1:
		name: "G2S1.wav"
		description: "Small anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAABP01.L.IR32", "SAABP01.R.IR32"]
		delay: [0, 1.5]

		b2:
		name: "G1S2.wav"
		description: "Small anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAABP01.L.IR32", "SAABP01.R.IR32"]
		delay: [0, 1.5]

		b3:
		name: "G6S3.wav"
		description: "Small anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAABP01.L.IR32", "SAABP01.R.IR32"]
		delay: [0, 1.5]

		b4:
		name: "G5S4.wav"
		description: "Small anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAABP01.L.IR32", "SAABP01.R.IR32"]
		delay: [0, 1.5]

		b5:
		name: "G4S5.wav"
		description: "Small anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAABP01.L.IR32", "SAABP01.R.IR32"]
		delay: [0, 1.5]

		b6:
		name: "G3S6.wav"
		description: "Small anechoic room with AB microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAABP01.L.IR32", "SAABP01.R.IR32"]
		delay: [0, 1.5]

		c1:
		name: "G3S1.wav"
		description: "Small anechoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAMSP01.L.IR32", "SAMSP01.R.IR32"]
		delay: [0, 0]

		c2:
		name: "G2S2.wav"
		description: "Small anechoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAMSP01.L.IR32", "SAMSP01.R.IR32"]
		delay: [0, 0]

		c3:
		name: "G1S3.wav"
		description: "Small anechoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAMSP01.L.IR32", "SAMSP01.R.IR32"]
		delay: [0, 0]

		c4:
		name: "G6S4.wav"
		description: "Small anechoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAMSP01.L.IR32", "SAMSP01.R.IR32"]
		delay: [0, 1]

		c5:
		name: "G5S5.wav"
		description: "Small anechoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAMSP01.L.IR32", "SAMSP01.R.IR32"]
		delay: [0, 0]

		c6:
		name: "G4S6.wav"
		description: "Small anechoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SAMSP01.L.IR32", "SAMSP01.R.IR32"]
		delay: [0, 0]

		d1:
		name: "G4S1.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 1.5]

		d2:
		name: "G3S2.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 1.5]

		d3:
		name: "G3S2.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 1.5]

		d4:
		name: "G1S4.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 1.5]

		d5:
		name: "G6S5.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 1.5]

		d6:
		name: "G5S6.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 1.5]

		e1:
		name: "G5S1.wav"
		description: "Small echoic room with binaural microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEBIP01.L.IR32", "SEBIP01.R.IR32"]
		delay: [0, 1.5]

		e2:
		name: "G4S2.wav"
		description: "Small echoic room with binaural microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEBIP01.L.IR32", "SEBIP01.R.IR32"]
		delay: [0, 1.5]

		e3:
		name: "G3S3.wav"
		description: "Small echoic room with binaural microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEBIP01.L.IR32", "SEBIP01.R.IR32"]
		delay: [0, 1.5]

		e4:
		name: "G2S4.wav"
		description: "Small echoic room with binaural microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEBIP01.L.IR32", "SEBIP01.R.IR32"]
		delay: [0, 1.5]

		e5:
		name: "G1S5.wav"
		description: "Small echoic room with binaural microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEBIP01.L.IR32", "SEBIP01.R.IR32"]
		delay: [0, 1.5]

		e6:
		name: "G6S6.wav"
		description: "Small echoic room with binaural microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEBIP01.L.IR32", "SEBIP01.R.IR32"]
		delay: [0, 1.5]

		f1:
		name: "G6S1.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 0]

		f2:
		name: "G5S2.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 0]

		f3:
		name: "G4S3.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 0]

		f4:
		name: "G3S4.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 0]

		f5:
		name: "G2S5.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 0]

		f6:
		name: "G1S6.wav"
		description: "Small echoic room with MS microphone pickup."
		source: ["test_double.wav", "test_double.wav"]
		IR: ["SEMSP01.L.IR32", "SEMSP01.R.IR32"]
		delay: [0, 0]

		No newline at end of file

item_generation_scripts/processing/process_ism_items.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -227,7 +227,7 @@ def generate_ism_items(
		# generate .csv filename (should end with .0.csv, .1.csv, ...)
		csv_filename = os.path.normpath(f"{output_filename}.{i}.csv")

		with open(os.path.join(output_path, csv_filename), "w") as f:
		with open(os.path.join(output_path, csv_filename), 'w', newline='', encoding='utf-8') as f:
		# create csv writer
		writer = csv.writer(f)