change overlap/gap to -1.0/+1.0s (7bcde644) · Commits · IVAS Codec Public Collaboration / IVAS Processing Scripts

item_gen_configs/ISM2_CONFIG.yml

+38 −38

Original line number	Diff line number	Diff line
		@@ -24,8 +24,8 @@ output_path: "./items_ISM2"
		loudness: -26

		### Pre-amble and Post-amble length in seconds (default = 0.0)
		preamble: 0.5
		postamble: 0.5
		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
		@@ -55,7 +55,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [0, 50]
		elevation: [0, 0]
		overlap: -0.5
		overlap: -1.0

		a2:
		name: "G6S2.wav"
		@@ -63,7 +63,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [50, 350]
		elevation: [0, 0]
		overlap: -0.5
		overlap: -1.0

		a3:
		name: "G5S3.wav"
		@@ -71,7 +71,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [40, 290]
		elevation: [0, 0]
		overlap: -0.5
		overlap: -1.0

		a4:
		name: "G4S4.wav"
		@@ -79,7 +79,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [30, 230]
		elevation: [15, 15]
		overlap: -0.5
		overlap: -1.0

		a5:
		name: "G3S5.wav"
		@@ -87,7 +87,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [20, 170]
		elevation: [15, 15]
		overlap: -0.5
		overlap: -1.0

		a6:
		name: "G2S6.wav"
		@@ -95,7 +95,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [10, 110]
		elevation: [15, 15]
		overlap: -0.5
		overlap: -1.0

		b1:
		name: "G2S1.wav"
		@@ -103,7 +103,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [20, 170]
		elevation: [30, 30]
		overlap: 0.5
		overlap: 1.0

		b2:
		name: "G1S2.wav"
		@@ -111,7 +111,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [10, 110]
		elevation: [30, 30]
		overlap: 0.5
		overlap: 1.0

		b3:
		name: "G6S3.wav"
		@@ -119,7 +119,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [0, 50]
		elevation: [30, 30]
		overlap: 0.5
		overlap: 1.0

		b4:
		name: "G5S4.wav"
		@@ -127,7 +127,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [50, 350]
		elevation: [60, 60]
		overlap: 0.5
		overlap: 1.0

		b5:
		name: "G4S5.wav"
		@@ -135,7 +135,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [40, 290]
		elevation: [60, 60]
		overlap: 0.5
		overlap: 1.0

		b6:
		name: "G3S6.wav"
		@@ -143,7 +143,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [30, 230]
		elevation: [60, 60]
		overlap: 0.5
		overlap: 1.0

		c1:
		name: "G3S1.wav"
		@@ -151,7 +151,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [40, 290]
		elevation: [0, 60]
		overlap: -0.5
		overlap: -1.0

		c2:
		name: "G2S2.wav"
		@@ -159,7 +159,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [30, 230]
		elevation: [0, 60]
		overlap: -0.5
		overlap: -1.0

		c3:
		name: "G1S3.wav"
		@@ -167,7 +167,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [20, 170]
		elevation: [0, 60]
		overlap: -0.5
		overlap: -1.0

		c4:
		name: "G6S4.wav"
		@@ -175,7 +175,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [10, 110]
		elevation: [0, 60]
		overlap: [0, 1]
		overlap: -1.0

		c5:
		name: "G5S5.wav"
		@@ -183,7 +183,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [0, 50]
		elevation: [0, 60]
		overlap: -0.5
		overlap: -1.0

		c6:
		name: "G4S6.wav"
		@@ -191,7 +191,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [50, 350]
		elevation: [0, 60]
		overlap: -0.5
		overlap: -1.0

		d1:
		name: "G4S1.wav"
		@@ -199,7 +199,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [50, "180:1:120 + 360"]
		elevation: [0, 60]
		overlap: 0.5
		overlap: 1.0

		d2:
		name: "G3S2.wav"
		@@ -207,7 +207,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [300, "-70:-1:-10 - 360"]
		elevation: [0, 60]
		overlap: 0.5
		overlap: 1.0

		d3:
		name: "G2S3.wav"
		@@ -215,7 +215,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [250, "-20:-1:-320"]
		elevation: [0, 60]
		overlap: 0.5
		overlap: 1.0

		d4:
		name: "G1S4.wav"
		@@ -223,7 +223,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [200, "30:-1:-270"]
		elevation: [0, 60]
		overlap: 0.5
		overlap: 1.0

		d5:
		name: "G6S5.wav"
		@@ -231,7 +231,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [150, "80:1:20 + 360"]
		elevation: [0, 60]
		overlap: 0.5
		overlap: 1.0

		d6:
		name: "G5S6.wav"
		@@ -239,7 +239,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: [100, "130:1:70 + 360"]
		elevation: [0, 60]
		overlap: 0.5
		overlap: 1.0

		e1:
		name: "G5S1.wav"
		@@ -247,7 +247,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["80:1:20 + 360", "80:1:20 + 360"]
		elevation: [10, 60]
		overlap: 0.5
		overlap: 1.0

		e2:
		name: "G4S2.wav"
		@@ -255,7 +255,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["130:1:70 + 360", "130:1:70 + 360"]
		elevation: [10, 60]
		overlap: 0.5
		overlap: 1.0

		e3:
		name: "G3S3.wav"
		@@ -263,7 +263,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["180:1:120 + 360", "180:1:120 + 360"]
		elevation: [10, 60]
		overlap: 0.5
		overlap: 1.0

		e4:
		name: "G2S4.wav"
		@@ -271,7 +271,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["-70:-1:-10 - 360", "-70:-1:-10 - 360"]
		elevation: [10, 60]
		overlap: 0.5
		overlap: 1.0

		e5:
		name: "G1S5.wav"
		@@ -279,7 +279,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["-20:-1:-320", "-20:-1:-320"]
		elevation: [10, 60]
		overlap: 0.5
		overlap: 1.0

		e6:
		name: "G6S6.wav"
		@@ -287,7 +287,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["30:-1:-270", "30:-1:-270"]
		elevation: [10, 60]
		overlap: 0.5
		overlap: 1.0

		f1:
		name: "G6S1.wav"
		@@ -295,7 +295,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["60:1:0 + 360", "60:-1:120 - 360"]
		elevation: [20, 50]
		overlap: -0.5
		overlap: -1.0

		f2:
		name: "G5S2.wav"
		@@ -303,7 +303,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["0:1:300", "0:-1:60 - 360"]
		elevation: [20, 50]
		overlap: -0.5
		overlap: -1.0

		f3:
		name: "G4S3.wav"
		@@ -311,7 +311,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["300:1:240 + 360", "300:-1:0"]
		elevation: [20, 50]
		overlap: -0.5
		overlap: -1.0

		f4:
		name: "G3S4.wav"
		@@ -319,7 +319,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["240:1:180 + 360", "240:-1:-60"]
		elevation: [20, 50]
		overlap: -0.5
		overlap: -1.0

		f5:
		name: "G2S5.wav"
		@@ -327,7 +327,7 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["180:1:120 + 360", "180:-1:-120"]
		elevation: [20, 50]
		overlap: -0.5
		overlap: -1.0

		f6:
		name: "G1S6.wav"
		@@ -335,5 +335,5 @@ scenes:
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		azimuth: ["120:1:60 + 360", "120:-1:180 - 360"]
		elevation: [20, 50]
		overlap: -0.5
		overlap: -1.0

		No newline at end of file

item_gen_configs/STEREO_CONFIG.yml

+38 −38

Original line number	Diff line number	Diff line
		@@ -30,8 +30,8 @@ output_path: "./items_STEREO"
		loudness: -26

		### Pre-amble and Post-amble length in seconds (default = 0.0)
		preamble: 0.5
		postamble: 0.5
		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
		@@ -54,250 +54,250 @@ scenes:
		description: "Two speakers sitting at oval table in opposite corners in a large echoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LEABP04.wav", "LEABP11.wav"]
		overlap: 0.5
		overlap: 1.0

		a2:
		name: "G6S2.wav"
		description: "Two speakers sitting at oval table in opposite corners in a large echoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LEABP05.wav", "LEABP11.wav"]
		overlap: 0.5
		overlap: 1.0

		a3:
		name: "G5S3.wav"
		description: "Two speakers sitting at oval table in opposite corners in a large echoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LEABP06.wav", "LEABP11.wav"]
		overlap: 0.5
		overlap: 1.0

		a4:
		name: "G4S4.wav"
		description: "Two speakers sitting at oval table in opposite corners in a large echoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LEABP05.wav", "LEABP10.wav"]
		overlap: -0.5
		overlap: -1.0

		a5:
		name: "G3S5.wav"
		description: "Two speakers sitting at oval table in opposite corners in a large echoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LEABP05.wav", "LEABP11.wav"]
		overlap: -0.5
		overlap: -1.0

		a6:
		name: "G2S6.wav"
		description: "Two speakers sitting at oval table in opposite corners in a large echoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LEABP05.wav", "LEABP12.wav"]
		overlap: -0.5
		overlap: -1.0

		b1:
		name: "G2S1.wav"
		description: "Two speakers sitting at oval table side by side in a large anechoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LAABP05.wav", "LAABP06.wav"]
		overlap: -0.5
		overlap: -1.0

		b2:
		name: "G1S2.wav"
		description: "Two speakers sitting at oval table side by side in a large anechoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LAABP07.wav", "LAABP08.wav"]
		overlap: 0.5
		overlap: 1.0

		b3:
		name: "G6S3.wav"
		description: "Two speakers sitting at oval table side by side in a large anechoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LAABP09.wav", "LAABP10.wav"]
		overlap: 0.5
		overlap: 1.0

		b4:
		name: "G5S4.wav"
		description: "Two speakers sitting at oval table side by side in a large anechoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LAABP11.wav", "LAABP12.wav"]
		overlap: -0.5
		overlap: -1.0

		b5:
		name: "G4S5.wav"
		description: "Two speakers sitting at oval table side by side in a large anechoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LAABP01.wav", "LAABP02.wav"]
		overlap: -0.5
		overlap: -1.0

		b6:
		name: "G3S6.wav"
		description: "Two speakers sitting at oval table side by side in a large anechoic conference room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["LAABP03.wav", "LAABP04.wav"]
		overlap: -0.5
		overlap: -1.0

		c1:
		name: "G3S1.wav"
		description: "One talker sitting at table in a small anechoic conference room."
		source: ["test_single.wav"]
		IR: ["SAMSP01.wav"]
		overlap: -0.5
		overlap: -1.0

		c2:
		name: "G2S2.wav"
		description: "One talker sitting at table in a small anechoic conference room."
		source: ["test_single.wav"]
		IR: ["SAMSP04.wav"]
		overlap: -0.5
		overlap: -1.0

		c3:
		name: "G1S3.wav"
		description: "One talker sitting at table in a small anechoic conference room."
		source: ["test_single.wav"]
		IR: ["SAMSP07.wav"]
		overlap: -0.5
		overlap: -1.0

		c4:
		name: "G6S4.wav"
		description: "One talker sitting at table in a small echoic conference room."
		source: ["test_single.wav"]
		IR: ["SEABP01.wav"]
		overlap: -0.5
		overlap: -1.0

		c5:
		name: "G5S5.wav"
		description: "One talker sitting at table in a small echoic conference room."
		source: ["test_single.wav"]
		IR: ["SEABP03.wav"]
		overlap: -0.5
		overlap: -1.0

		c6:
		name: "G4S6.wav"
		description: "One talker sitting at table in a small echoic conference room."
		source: ["test_single.wav"]
		IR: ["SEABP06.wav"]
		overlap: -0.5
		overlap: -1.0

		d1:
		name: "G4S1.wav"
		description: "One talker sitting at table in a small anechoic conference room."
		source: ["test_single.wav"]
		IR: ["SEBIP01.wav"]
		overlap: -0.5
		overlap: -1.0

		d2:
		name: "G3S2.wav"
		description: "One talker sitting at table in a small anechoic conference room."
		source: ["test_single.wav"]
		IR: ["SEBIP04.wav"]
		overlap: -0.5
		overlap: -1.0

		d3:
		name: "G3S2.wav"
		description: "One talker sitting at table in a small anechoic conference room."
		source: ["test_single.wav"]
		IR: ["SEBIP07.wav"]
		overlap: -0.5
		overlap: -1.0

		d4:
		name: "G1S4.wav"
		description: "One talker sitting at table in a small echoic conference room."
		source: ["test_single.wav"]
		IR: ["SEBIP07.wav"]
		overlap: -0.5
		overlap: -1.0

		d5:
		name: "G6S5.wav"
		description: "One talker sitting at table in a small echoic conference room."
		source: ["test_single.wav"]
		IR: ["SEBIP07.wav"]
		overlap: -0.5
		overlap: -1.0

		d6:
		name: "G5S6.wav"
		description: "One talker sitting at table in a small echoic conference room."
		source: ["test_single.wav"]
		IR: ["SEBIP07.wav"]
		overlap: -0.5
		overlap: -1.0

		e1:
		name: "G5S1.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEMSP01.wav", "SEMSP03.wav"]
		overlap: 0.5
		overlap: 1.0

		e2:
		name: "G4S2.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEMSP01.wav", "SEMSP05.wav"]
		overlap: 0.5
		overlap: 1.0

		e3:
		name: "G3S3.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEMSP01.wav", "SEMSP07.wav"]
		overlap: 0.5
		overlap: 1.0

		e4:
		name: "G2S4.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEMSP03.wav", "SEMSP04.wav"]
		overlap: -0.5
		overlap: -1.0

		e5:
		name: "G1S5.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEMSP05.wav", "SEMSP07.wav"]
		overlap: -0.5
		overlap: -1.0

		e6:
		name: "G6S6.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEMSP06.wav", "SEMSP02.wav"]
		overlap: -0.5
		overlap: -1.0

		f1:
		name: "G6S1.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEBIP05.wav", "SEBIP01.wav"]
		overlap: 0.5
		overlap: 1.0

		f2:
		name: "G5S2.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEBIP07.wav", "SEBIP01.wav"]
		overlap: 0.5
		overlap: 1.0

		f3:
		name: "G4S3.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEBIP04.wav", "SEBIP01.wav"]
		overlap: 0.5
		overlap: 1.0

		f4:
		name: "G3S4.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEBIP02.wav", "SEBIP06.wav"]
		overlap: -0.5
		overlap: -1.0

		f5:
		name: "G2S5.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEBIP02.wav", "SEBIP06.wav"]
		overlap: -0.5
		overlap: -1.0

		f6:
		name: "G1S6.wav"
		description: "Two talkers sitting in a room."
		source: ["test_talker1_trimmed.wav", "test_talker2_trimmed.wav"]
		IR: ["SEBIP03.wav", "SEBIP04.wav"]
		overlap: -0.5
		overlap: -1.0

		No newline at end of file