new naming convention from IVAS-7a in STERO tests (f21915ae) · Commits · IVAS Codec Public Collaboration / IVAS Processing Scripts

item_gen_configs/P800-6.yml

+50 −40

Original line number	Diff line number	Diff line
		@@ -35,7 +35,7 @@ add_low_level_random_noise: true
		### Scene description
		################################################

		### Each scene must start with the sceneN tag
		### Each scene must start with a unique 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
		@@ -44,13 +44,23 @@ add_low_level_random_noise: true
		### 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]

		### Naming convention for P.800 items
		### The filenames of the input content samples are represented by:
		### leeeayszz.wav
		### The filenames of the accompanying 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 through d according to Table 2)
		### eee stands for the experiment designator, e.g. p01 (see Table 1)
		### a stands audio, and y is the per experiment category according to IVAS-8a
		### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07, where 07 is the preliminary
		### o stands for object number; 0, 1, 2, 3

		scenes:
		a1:
		name: "G1S1.wav"
		name: "lp06a1s01"
		description: "Talker sitting at a table"
		source: ["m1_s1.wav", "m1_s7.wav"]
		azimuth: 0
		@@ -58,7 +68,7 @@ scenes:
		overlap: -0.5

		a2:
		name: "G6S2.wav"
		name: "lp06a1s02"
		description: "Talker sitting at a table"
		source: ["f3_s2.wav", "f3_s8.wav"]
		azimuth: 60
		@@ -66,238 +76,238 @@ scenes:
		overlap: -0.5

		a3:
		name: "G5S3.wav"
		name: "lp06a1s03"
		description: "Talker sitting at a table"
		source: ["m3_s3.wav", "m3_s9.wav"]
		azimuth: 120
		elevation: 0

		a4:
		name: "G4S4.wav"
		name: "lp06a1s04"
		description: "Talker sitting at a table"
		source: ["f2_s4.wav", "f2_s10.wav"]
		azimuth: 180
		elevation: 0

		a5:
		name: "G3S5.wav"
		name: "lp06a1s05"
		description: "Talker sitting at a table"
		source: ["m2_s5.wav", "m2_s11.wav"]
		azimuth: 240
		elevation: 0

		a6:
		name: "G2S6.wav"
		name: "lp06a1s06"
		description: "Talker sitting at a table"
		source: ["f1_s6.wav", "f1_s12.wav"]
		azimuth: 300
		elevation: 0

		b1:
		name: "G2S1.wav"
		name: "lp06a2s01"
		description: "standing talker."
		source: ["f1_s1.wav", "f1_s7.wav"]
		azimuth: 120
		elevation: 35

		b2:
		name: "G1S2.wav"
		name: "lp06a2s02"
		description: "standing talker."
		source: ["m1_s2.wav", "m1_s8.wav"]
		azimuth: 180
		elevation: 35

		b3:
		name: "G6S3.wav"
		name: "lp06a2s03"
		description: "standing talker."
		source: ["f3_s3.wav", "f3_s9.wav"]
		azimuth: 240
		elevation: 35

		b4:
		name: "G5S4.wav"
		name: "lp06a2s04"
		description: "standing talker."
		source: ["m3_s4.wav", "m3_s10.wav"]
		azimuth: 300
		elevation: 35

		b5:
		name: "G4S5.wav"
		name: "lp06a2s05"
		description: "standing talker."
		source: ["f2_s5.wav", "f2_s11.wav"]
		azimuth: 0
		elevation: 35

		b6:
		name: "G3S6.wav"
		name: "lp06a2s06"
		description: "standing talker."
		source: ["m2_s6.wav", "m2_s12.wav"]
		azimuth: 60
		elevation: 35

		c1:
		name: "G3S1.wav"
		name: "lp06a3s01"
		description: "Smaller talker (child) walking around a table."
		source: ["m2_s1.wav", "m2_s7.wav"]
		azimuth: "0:1:360"
		elevation: 0

		c2:
		name: "G2S2.wav"
		name: ""lp06a3s02"
		description: "Smaller talker (child) walking around a table."
		source: ["f1_s2.wav", "f1_s8.wav"]
		azimuth: "60:1:60+360"
		elevation: 0

		c3:
		name: "G1S3.wav"
		name: "lp06a3s03"
		description: "Smaller talker (child) walking around a table."
		source: ["m1_s3.wav", "m1_s9.wav"]
		azimuth: "120:1:120+360"
		elevation: 0

		c4:
		name: "G6S4.wav"
		name: "lp06a3s04"
		description: "Smaller talker (child) walking around a table."
		source: ["f3_s4.wav", "f3_s10.wav"]
		azimuth: "180:1:180+360"
		elevation: 0

		c5:
		name: "G5S5.wav"
		name: "lp06a3s05"
		description: "Smaller talker (child) walking around a table."
		source: ["m3_s5.wav", "m3_s11.wav"]
		azimuth: "240:1:240+360"
		elevation: 0

		c6:
		name: "G4S6.wav"
		name: "lp06a3s06"
		description: "Smaller talker (child) walking around a table."
		source: ["f2_s6.wav", "f2_s12.wav"]
		azimuth: "300:1:300+360"
		elevation: 0

		d1:
		name: "G4S1.wav"
		name: "lp06a4s01"
		description: "Talker walking around the table."
		source: ["f2_s1.wav", "f2_s7.wav"]
		azimuth: "0:-1:-360"
		elevation: 35

		d2:
		name: "G3S2.wav"
		name: "lp06a4s02"
		description: "Talker walking around the table."
		source: ["m2_s2.wav", "m2_s8.wav"]
		azimuth: "60:-1:60-360"
		elevation: 35

		d3:
		name: "G2S3.wav"
		name: "lp06a4s03"
		description: "Talker walking around the table."
		source: ["f1_s3.wav", "f1_s9.wav"]
		azimuth: "120:-1:120-360"
		elevation: 35

		d4:
		name: "G1S4.wav"
		name: "lp06a4s04"
		description: "Talker walking around the table."
		source: ["m1_s4.wav", "m1_s10.wav"]
		azimuth: "180:-1:180-360"
		elevation: 35

		d5:
		name: "G6S5.wav"
		name: "lp06a4s05"
		description: "Talker walking around the table."
		source: ["f3_s5.wav", "f3_s11.wav"]
		azimuth: "240:-1:240-360"
		elevation: 35

		d6:
		name: "G5S6.wav"
		name: "lp06a4s06"
		description: "Talker walking around the table."
		source: ["m3_s6.wav", "m3_s12.wav"]
		azimuth: "300:-1:300-360"
		elevation: 35

		e1:
		name: "G5S1.wav"
		name: "lp06a5s01"
		description: "Elevation displacement."
		source: ["m3_s1.wav", "m3_s7.wav"]
		azimuth: 240
		elevation: "-90:0.5:90"

		e2:
		name: "G4S2.wav"
		name: "lp06a5s02"
		description: "Elevation displacement."
		source: ["f2_s2.wav", "f2_s8.wav"]
		azimuth: 300
		elevation: 0

		e3:
		name: "G3S3.wav"
		name: "lp06a5s03"
		description: "Elevation displacement."
		source: ["m2_s3.wav", "m2_s9.wav"]
		azimuth: 0
		elevation: "-90:0.5:90"

		e4:
		name: "G2S4.wav"
		name: "lp06a5s04"
		description: "Elevation displacement."
		source: ["f1_s4.wav", "f1_s10.wav"]
		azimuth: 60
		elevation: "-90:0.5:90"

		e5:
		name: "G1S5.wav"
		name: "lp06a5s05"
		description: "Elevation displacement."
		source: ["m1_s5.wav", "m1_s11.wav"]
		azimuth: 120
		elevation: "-90:0.5:90"

		e6:
		name: "G6S6.wav"
		name: "lp06a5s06"
		description: "Elevation displacement."
		source: ["f3_s6.wav", "f3_s12.wav"]
		azimuth: 180
		elevation: "-90:0.5:90"

		f1:
		name: "G6S1.wav"
		name: "lp06a6s01"
		description: "Azimuth and elevation displacement."
		source: ["f3_s1.wav", "f3_s7.wav"]
		azimuth: "60:0.5:60+180"
		elevation: "35:-0.2:-35"

		f2:
		name: "G5S2.wav"
		name: "lp06a6s02"
		description: "Azimuth and elevation displacement."
		source: ["m3_s2.wav", "m3_s8.wav"]
		azimuth: "120:0.5:120+180"
		elevation: "35:-0.2:-35"

		f3:
		name: "G4S3.wav"
		name: "lp06a6s03"
		description: "Azimuth and elevation displacement."
		source: ["f2_s3.wav", "f2_s9.wav"]
		azimuth: "180:0.5:180+180"
		elevation: "35:-0.2:-35"

		f4:
		name: "G3S4.wav"
		name: "lp06a6s04"
		description: "Azimuth and elevation displacement."
		source: ["m2_s4.wav", "m2_s10.wav"]
		azimuth: "240:0.5:240+180"
		elevation: "35:-0.2:-35"

		f5:
		name: "G2S5.wav"
		name: "lp06a6s05"
		description: "Azimuth and elevation displacement."
		source: ["f1_s5.wav", "f1_s11.wav"]
		azimuth: "300:0.5:300+180"
		elevation: "35:-0.2:-35"

		f6:
		name: "G1S6.wav"
		name: "lp06a6s06"
		description: "Azimuth and elevation displacement."
		source: ["m1_s6.wav", "m1_s12.wav"]
		azimuth: "0:0.5:0+180"

item_gen_configs/P800-7.yml

+50 −41

Original line number	Diff line number	Diff line
		@@ -34,23 +34,32 @@ add_low_level_random_noise: true
		### Scene description
		################################################

		### Each scene must start with the sceneN tag
		### Each scene must start with a unique 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 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

		### 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]

		### Naming convention for P.800 items
		### The filenames of the input content samples are represented by:
		### leeeayszz.wav
		### The filenames of the accompanying 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 through d according to Table 2)
		### eee stands for the experiment designator, e.g. p01 (see Table 1)
		### a stands audio, and y is the per experiment category according to IVAS-8a
		### s stands for sample and zz is the sample number; 01, 02, 03, 04, 05, 06, 07, where 07 is the preliminary
		### o stands for object number; 0, 1, 2, 3

		scenes:
		a1:
		name: "G1S1.wav"
		name: "lp07a1s01"
		description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances."
		source: ["m1_s1.wav", "f1_s1.wav"]
		azimuth: [0, 50]
		@@ -58,7 +67,7 @@ scenes:
		overlap: -1.0

		a2:
		name: "G6S2.wav"
		name: "lp07a1s02"
		description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances."
		source: ["f3_s8.wav", "m1_s8.wav"]
		azimuth: [50, 350]
		@@ -66,7 +75,7 @@ scenes:
		overlap: -1.0

		a3:
		name: "G5S3.wav"
		name: "lp07a1s03"
		description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances."
		source: ["f2_s9.wav", "m3_s9.wav"]
		azimuth: [40, 290]
		@@ -74,7 +83,7 @@ scenes:
		overlap: -1.0

		a4:
		name: "G4S4.wav"
		name: "lp07a1s04"
		description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances."
		source: ["f1_s10.wav", "m2_s10.wav"]
		azimuth: [30, 230]
		@@ -82,7 +91,7 @@ scenes:
		overlap: -1.0

		a5:
		name: "G3S5.wav"
		name: "lp07a1s05"
		description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances."
		source: ["m3_s5.wav", "f3_s5.wav"]
		azimuth: [20, 170]
		@@ -90,7 +99,7 @@ scenes:
		overlap: -1.0

		a6:
		name: "G2S6.wav"
		name: "lp07a1s06"
		description: "Two talkers sitting at a table, at different azimuth angles with respect to the microphone, non-overlapping utterances."
		source: ["m2_s6.wav", "f2_s6.wav"]
		azimuth: [10, 110]
		@@ -98,7 +107,7 @@ scenes:
		overlap: -1.0

		b1:
		name: "G2S1.wav"
		name: "lp07a2s01"
		description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."
		source: ["m2_s1.wav", "f2_s1.wav"]
		azimuth: [20, 170]
		@@ -106,7 +115,7 @@ scenes:
		overlap: 1.0

		b2:
		name: "G1S2.wav"
		name: "lp07a2s02"
		description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."
		source: ["m1_s2.wav", "f1_s2.wav"]
		azimuth: [10, 110]
		@@ -114,7 +123,7 @@ scenes:
		overlap: 1.0

		b3:
		name: "G6S3.wav"
		name: "lp07a2s03"
		description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."
		source: ["f3_s9.wav", "m1_s9.wav"]
		azimuth: [0, 50]
		@@ -122,7 +131,7 @@ scenes:
		overlap: 1.0

		b4:
		name: "G5S4.wav"
		name: "lp07a2s04"
		description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."
		source: ["f2_s10.wav", "m3_s10.wav"]
		azimuth: [50, 350]
		@@ -130,7 +139,7 @@ scenes:
		overlap: 1.0

		b5:
		name: "G4S5.wav"
		name: "lp07a2s05"
		description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."
		source: ["f1_s11.wav", "m2_s11.wav"]
		azimuth: [40, 290]
		@@ -138,7 +147,7 @@ scenes:
		overlap: 1.0

		b6:
		name: "G3S6.wav"
		name: "lp07a2s06"
		description: "Two standing talkers, at different azimuth angles with respect to the microphone, ~30% overlapping utterances."
		source: ["m3_s6.wav", "f3_s6.wav"]
		azimuth: [30, 230]
		@@ -146,7 +155,7 @@ scenes:
		overlap: 1.0

		c1:
		name: "G3S1.wav"
		name: "lp07a3s01"
		description: "one talker sitting at a table, second talker standing beside the table, non-overlapping utterances."
		source: ["m3_s1.wav", "f3_s1.wav"]
		azimuth: [40, 290]
		@@ -154,7 +163,7 @@ scenes:
		overlap: -1.0

		c2:
		name: "G2S2.wav"
		name: "lp07a3s02"
		description: "one talker sitting at a table, second talker standing beside the table, non-overlapping utterances."
		source: ["m2_s2.wav", "f2_s2.wav"]
		azimuth: [30, 230]
		@@ -162,7 +171,7 @@ scenes:
		overlap: -1.0

		c3:
		name: "G1S3.wav"
		name: "lp07a3s03"
		description: "one talker sitting at a table, second talker standing beside the table, non-overlapping utterances."
		source: ["m1_s3.wav", "f1_s3.wav"]
		azimuth: [20, 170]
		@@ -170,7 +179,7 @@ scenes:
		overlap: -1.0

		c4:
		name: "G6S4.wav"
		name: "lp07a3s04"
		description: "one talker sitting at a table, second talker standing beside the table, non-overlapping utterances."
		source: ["f3_s10.wav", "m1_s10.wav"]
		azimuth: [10, 110]
		@@ -178,7 +187,7 @@ scenes:
		overlap: -1.0

		c5:
		name: "G5S5.wav"
		name: "lp07a3s05"
		description: "one talker sitting at a table, second talker standing beside the table, non-overlapping utterances."
		source: ["f2_s11.wav", "m3_s11.wav"]
		azimuth: [0, 50]
		@@ -186,7 +195,7 @@ scenes:
		overlap: -1.0

		c6:
		name: "G4S6.wav"
		name: "lp07a3s06"
		description: "one talker sitting at a table, second talker standing beside the table, non-overlapping utterances."
		source: ["f1_s12.wav", "m2_s12.wav"]
		azimuth: [50, 350]
		@@ -194,7 +203,7 @@ scenes:
		overlap: -1.0

		d1:
		name: "G4S1.wav"
		name: "lp07a4s01"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["f1_s7.wav", "m2_s7.wav"]
		azimuth: [50, "180:1:120 + 360"]
		@@ -202,7 +211,7 @@ scenes:
		overlap: 1.0

		d2:
		name: "G3S2.wav"
		name: "lp07a4s02"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["m3_s2.wav", "f3_s2.wav"]
		azimuth: [300, "-70:-1:-10 - 360"]
		@@ -210,7 +219,7 @@ scenes:
		overlap: 1.0

		d3:
		name: "G2S3.wav"
		name: "lp07a4s03"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["m2_s3.wav", "f2_s3.wav"]
		azimuth: [250, "-20:-1:-320"]
		@@ -218,7 +227,7 @@ scenes:
		overlap: 1.0

		d4:
		name: "G1S4.wav"
		name: "lp07a4s04"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["m1_s4.wav", "f1_s4.wav"]
		azimuth: [200, "30:-1:-270"]
		@@ -226,7 +235,7 @@ scenes:
		overlap: 1.0

		d5:
		name: "G6S5.wav"
		name: "lp07a4s05"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["f3_s11.wav", "m1_s11.wav"]
		azimuth: [150, "80:1:20 + 360"]
		@@ -234,7 +243,7 @@ scenes:
		overlap: 1.0

		d6:
		name: "G5S6.wav"
		name: "lp07a4s06"
		description: "one talker sitting at a table, second talker walking around the table, ~30% overlapping utterances."
		source: ["f2_s12.wav", "m3_s12.wav"]
		azimuth: [100, "130:1:70 + 360"]
		@@ -242,7 +251,7 @@ scenes:
		overlap: 1.0

		e1:
		name: "G5S1.wav"
		name: "lp07a5s01"
		description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances"
		source: ["f2_s7.wav", "m3_s7.wav"]
		azimuth: ["80:1:20 + 360", "80:1:20 + 360"]
		@@ -250,7 +259,7 @@ scenes:
		overlap: 1.0

		e2:
		name: "G4S2.wav"
		name: "lp07a5s02"
		description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances"
		source: ["f1_s8.wav", "m2_s8.wav"]
		azimuth: ["130:1:70 + 360", "130:1:70 + 360"]
		@@ -258,7 +267,7 @@ scenes:
		overlap: 1.0

		e3:
		name: "G3S3.wav"
		name: "lp07a5s03"
		description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances"
		source: ["m3_s3.wav", "f3_s3.wav"]
		azimuth: ["180:1:120 + 360", "180:1:120 + 360"]
		@@ -266,7 +275,7 @@ scenes:
		overlap: 1.0

		e4:
		name: "G2S4.wav"
		name: "lp07a5s04"
		description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances"
		source: ["m2_s4.wav", "f2_s4.wav"]
		azimuth: ["-70:-1:-10 - 360", "-70:-1:-10 - 360"]
		@@ -274,7 +283,7 @@ scenes:
		overlap: 1.0

		e5:
		name: "G1S5.wav"
		name: "lp07a5s05"
		description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances"
		source: ["m1_s5.wav", "f1_s5.wav"]
		azimuth: ["-20:-1:-320", "-20:-1:-320"]
		@@ -282,7 +291,7 @@ scenes:
		overlap: 1.0

		e6:
		name: "G6S6.wav"
		name: "lp07a5s06"
		description: "Two talkers walking side-by-side around the table, ~30% overlapping utterances"
		source: ["f3_s12.wav", "m1_s12.wav"]
		azimuth: ["30:-1:-270", "30:-1:-270"]
		@@ -290,7 +299,7 @@ scenes:
		overlap: 1.0

		f1:
		name: "G6S1.wav"
		name: "lp07a6s01"
		description: "Two talkers walking around the table in opposite directions, non-overlapping utterances."
		source: ["f3_s7.wav", "m1_s7.wav"]
		azimuth: ["60:1:0 + 360", "60:-1:120 - 360"]
		@@ -298,7 +307,7 @@ scenes:
		overlap: -1.0

		f2:
		name: "G5S2.wav"
		name: "lp07a6s02"
		description: "Two talkers walking around the table in opposite directions, non-overlapping utterances."
		source: ["f2_s8.wav", "m3_s8.wav"]
		azimuth: ["0:1:300", "0:-1:60 - 360"]
		@@ -306,7 +315,7 @@ scenes:
		overlap: -1.0

		f3:
		name: "G4S3.wav"
		name: "lp07a6s03"
		description: "Two talkers walking around the table in opposite directions, non-overlapping utterances."
		source: ["f1_s9.wav", "m2_s9.wav"]
		azimuth: ["300:1:240 + 360", "300:-1:0"]
		@@ -314,7 +323,7 @@ scenes:
		overlap: -1.0

		f4:
		name: "G3S4.wav"
		name: "lp07a6s04"
		description: "Two talkers walking around the table in opposite directions, non-overlapping utterances."
		source: ["m3_s4.wav", "f3_s4.wav"]
		azimuth: ["240:1:180 + 360", "240:-1:-60"]
		@@ -322,7 +331,7 @@ scenes:
		overlap: -1.0

		f5:
		name: "G2S5.wav"
		name: "lp07a6s05"
		description: "Two talkers walking around the table in opposite directions, non-overlapping utterances."
		source: ["m2_s5.wav", "f2_s5.wav"]
		azimuth: ["180:1:120 + 360", "180:-1:-120"]
		@@ -330,7 +339,7 @@ scenes:
		overlap: -1.0

		f6:
		name: "G1S6.wav"
		name: "lp07a6s06"
		description: "Two talkers walking around the table in opposite directions, non-overlapping utterances."
		source: ["m1_s6.wav", "f1_s6.wav"]
		azimuth: ["120:1:60 + 360", "120:-1:180 - 360"]