Fairness pitch

Overall scores

	w2v2-L	hubert-L	wavlm	data2vec
Overall Score	93.3% passed tests (14 passed / 1 failed).	100.0% passed tests (15 passed / 0 failed).	93.3% passed tests (14 passed / 1 failed).	93.3% passed tests (14 passed / 1 failed).

Concordance Correlation Coeff High Pitch

CCC high pitch - CCC combined.

Threshold: 0.1

Data	Concordance Correlation Coeff High Pitch
	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	-0.05	-0.04	0.00	-0.07
mean	-0.05	-0.04	0.00	-0.07

Concordance Correlation Coeff Low Pitch

CCC low pitch - CCC combined.

Threshold: 0.1

Data	Concordance Correlation Coeff Low Pitch
	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	0.04	0.02	0.02	0.04
mean	0.04	0.02	0.02	0.04

Concordance Correlation Coeff Medium Pitch

CCC medium pitch - CCC combined.

Threshold: 0.1

Data	Concordance Correlation Coeff Medium Pitch
	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	0.01	0.01	-0.02	0.04
mean	0.01	0.01	-0.02	0.04

Precision Per Bin High Pitch

Precision per bin high pitch - precision per bin combined. Bins with too few samples are skipped.

Threshold: 0.125

Data	(-inf, 0.25]				(0.25, 0.5]				(0.5, 0.75]				(0.75, inf]
	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard					0.04	0.03	0.06	0.06	-0.02	-0.01	0.01	-0.03
mean					0.04	0.03	0.06	0.06	-0.02	-0.01	0.01	-0.03

Precision Per Bin Low Pitch

Precision per bin low pitch - precision per bin combined. Bins with too few samples are skipped.

Threshold: 0.125

Data	(-inf, 0.25]				(0.25, 0.5]				(0.5, 0.75]				(0.75, inf]
	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard					-0.05	-0.07	-0.05	-0.06	0.03	0.02	0.03	0.05
mean					-0.05	-0.07	-0.05	-0.06	0.03	0.02	0.03	0.05

Precision Per Bin Medium Pitch

Precision per bin medium pitch - precision per bin combined. Bins with too few samples are skipped.

Threshold: 0.125

Data	(-inf, 0.25]				(0.25, 0.5]				(0.5, 0.75]				(0.75, inf]
	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard					0.05	0.06	0.02	0.04	-0.00	-0.01	-0.04	-0.01
mean					0.05	0.06	0.02	0.04	0.00	-0.01	-0.04	-0.01

Recall Per Bin High Pitch

Recall per bin high pitch - recall per bin combined. Bins with too few samples are skipped.

Threshold: 0.125

Data	(-inf, 0.25]				(0.25, 0.5]				(0.5, 0.75]				(0.75, inf]
	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard					-0.10	-0.03	-0.02	-0.12	0.04	0.03	0.04	0.00
mean					-0.10	-0.03	-0.02	-0.12	0.04	0.03	0.04	0.00

Recall Per Bin Low Pitch

Recall per bin low pitch - recall per bin combined. Bins with too few samples are skipped.

Threshold: 0.125

Data	(-inf, 0.25]				(0.25, 0.5]				(0.5, 0.75]				(0.75, inf]
	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard					0.14	0.05	0.13	0.15	-0.05	-0.05	-0.06	-0.03
mean					0.14	0.05	0.13	0.15	-0.05	-0.05	-0.06	-0.03

Recall Per Bin Medium Pitch

Recall per bin medium pitch - recall per bin combined. Bins with too few samples are skipped.

Threshold: 0.125

Data	(-inf, 0.25]				(0.25, 0.5]				(0.5, 0.75]				(0.75, inf]
	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec	w2v2-L	hubert-L	wavlm	data2vec
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard					-0.03	-0.03	-0.11	-0.03	0.02	0.02	0.02	0.02
mean					-0.03	-0.03	-0.11	-0.03	0.02	0.02	0.02	0.02

Visualization

w2v2-L	hubert-L	wavlm	data2vec