diff --git a/tools/aqua-listen/kits/voice-source/kit.json b/tools/aqua-listen/kits/voice-source/kit.json index bbdf5ad..1edd89b 100644 --- a/tools/aqua-listen/kits/voice-source/kit.json +++ b/tools/aqua-listen/kits/voice-source/kit.json @@ -10,7 +10,7 @@ "file": "saw_a.wav", "group": "pulse", "pair": "pulse-rosenberg", - "title": "Measured: HNR 29.9 dB, output rms 0.0530, peak 0.224. Scaffold source: band-limited saw through the tilt lowpass.", + "title": "Measured: HNR 30.3 dB, output rms 0.0537, peak 0.227. Scaffold source: band-limited saw through the tilt lowpass.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -18,7 +18,7 @@ "file": "ros.wav", "group": "pulse", "pair": "pulse-saw", - "title": "Measured: HNR 29.1 dB, output rms 0.0400 (-2.4 dB re saw), peak 0.102 (-6.8 dB). Band energy re total, 0-0.5/0.5-1.5/1.5-3/3-6 kHz: saw -2.3/-4.0/-24.0/-24.9 dB, Rosenberg -0.3/-12.4/-43.7/-40.3 dB. PREDICTION: darker and rounder than the saw, less buzz and edge, F2 of /i/ weaker; loudness the same (that last part is already falsified at the output: it is 2.4 dB quieter). FALSIFIED if no difference is heard, if it is heard as buzzier or brighter, or if it is heard as the same kazoo quality.", + "title": "Measured: HNR 29.5 dB, output rms 0.0401 (-2.5 dB re saw), peak 0.102 (-6.9 dB). Band energy re total, 0-0.5/0.5-1.5/1.5-3/3-6 kHz, from the render before the tract fix (a different FFT estimate on the new render differs by under 1 dB; not re-measured with the original method): saw -2.3/-4.0/-24.0/-24.9 dB, Rosenberg -0.3/-12.4/-43.7/-40.3 dB. PREDICTION: darker and rounder than the saw, less buzz and edge, F2 of /i/ weaker; loudness the same (that last part is already falsified at the output: it is 2.5 dB quieter). FALSIFIED if no difference is heard, if it is heard as buzzier or brighter, or if it is heard as the same kazoo quality.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -26,7 +26,7 @@ "file": "saw_b.wav", "group": "pulsematch", "pair": "pulsematch-rosenberg", - "title": "Measured: HNR 29.9 dB, output rms 0.0530, peak 0.224. Byte copy of pulse-saw's render.", + "title": "Measured: HNR 30.3 dB, output rms 0.0537, peak 0.227. Byte copy of pulse-saw's render.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -34,7 +34,7 @@ "file": "ros_matched.wav", "group": "pulsematch", "pair": "pulsematch-saw", - "title": "Measured: HNR 29.1 dB, output rms 0.0529 (matched to the saw), peak 0.135. The Rosenberg render times 1.324 (+2.44 dB). PREDICTION: the same darker, rounder voice as in pair 'pulse', and no longer the quieter one. FALSIFIED if at matched rms it is no longer heard as darker/rounder (then loudness carried the first pair), or if it is heard as louder or brighter.", + "title": "Measured: HNR 29.5 dB, output rms 0.0537 (matched to the saw), peak 0.137. The Rosenberg render times 1.341 (+2.55 dB). PREDICTION: the same darker, rounder voice as in pair 'pulse', and no longer the quieter one. FALSIFIED if at matched rms it is no longer heard as darker/rounder (then loudness carried the first pair), or if it is heard as louder or brighter.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -42,7 +42,7 @@ "file": "clean.wav", "group": "noise", "pair": "noise-hnr20", - "title": "Measured: HNR 29.9 dB, output rms 0.0530, peak 0.224. The scaffold's noise floor (0.05); noise 0 measures 30.8, the method's ceiling here.", + "title": "Measured: HNR 30.3 dB, output rms 0.0537, peak 0.227. The scaffold's noise floor (0.05); noise 0 measured 30.8 before the tract fix, the method's ceiling here.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -50,7 +50,7 @@ "file": "w20.wav", "group": "noise", "pair": "noise-clean", - "title": "Measured: HNR 19.8 dB, output rms 0.0532, peak 0.231. White glottal noise raised to 0.33. PREDICTION: audible breath/hiss under the voice; a listener who called the clean voice a kazoo or buzzer hears this as less pure-tone but still a machine. FALSIFIED if B is not noisier; if the noise is heard as a separate hiss stream not fused with the voice; or if A and B are the same kazoo to the same degree (then purity of the periodicity is not what makes it a kazoo).", + "title": "Measured: HNR 19.9 dB, output rms 0.0539, peak 0.242. White glottal noise raised to 0.33. PREDICTION: audible breath/hiss under the voice; a listener who called the clean voice a kazoo or buzzer hears this as less pure-tone but still a machine. FALSIFIED if B is not noisier; if the noise is heard as a separate hiss stream not fused with the voice; or if A and B are the same kazoo to the same degree (then purity of the periodicity is not what makes it a kazoo).", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -58,7 +58,7 @@ "file": "w20_b.wav", "group": "colour", "pair": "colour-hp20", - "title": "Measured: HNR 19.8 dB, output rms 0.0532, peak 0.231. Byte copy of noise-hnr20's render.", + "title": "Measured: HNR 19.9 dB, output rms 0.0539, peak 0.242. Byte copy of noise-hnr20's render.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -66,7 +66,7 @@ "file": "h20.wav", "group": "colour", "pair": "colour-white20", - "title": "Measured: HNR 20.1 dB, output rms 0.0532, peak 0.238. Noise high-passed at 2 kHz (2nd order), level 0.33. PREDICTION: reads as hiss or 's'-like air, more separable from the voice than the white noise at the same HNR; the white one reads as roughness or breathy voice. FALSIFIED if no difference is heard, or if B is less hissy than A.", + "title": "Measured: HNR 19.9 dB, output rms 0.0540, peak 0.238. Noise high-passed at 2 kHz (2nd order), level 0.33. PREDICTION: reads as hiss or 's'-like air, more separable from the voice than the white noise at the same HNR; the white one reads as roughness or breathy voice. FALSIFIED if no difference is heard, or if B is less hissy than A.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -74,7 +74,7 @@ "file": "h25.wav", "group": "aspiration", "pair": "aspiration-hp15", - "title": "Measured: HNR 25.7 dB, output rms 0.0530, peak 0.231. High-passed noise at level 0.165. PREDICTION: at most faintly airy, may be called no different from a clean voice. FALSIFIED if A is already clearly hissy.", + "title": "Measured: HNR 25.8 dB, output rms 0.0538, peak 0.231. High-passed noise at level 0.165. PREDICTION: at most faintly airy, may be called no different from a clean voice. FALSIFIED if A is already clearly hissy.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" }, { @@ -82,7 +82,7 @@ "file": "h15.wav", "group": "aspiration", "pair": "aspiration-hp25", - "title": "Measured: HNR 14.9 dB, output rms 0.0538, peak 0.250. High-passed noise at level 0.6. PREDICTION: clearly hissy, breathier than A. FALSIFIED if B is not hissier than A.", + "title": "Measured: HNR 14.9 dB, output rms 0.0546, peak 0.250. High-passed noise at level 0.6. PREDICTION: clearly hissy, breathier than A. FALSIFIED if B is not hissier than A.", "feel": "the short made-up phrase 'ah-mee' in a synthetic voice; listen to the voice itself (buzz, edge, breath), not the words" } ]