Robustness low quality phone

Overall scores

	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
Overall Score	0.0% passed tests (0 passed / 4 failed).	75.0% passed tests (3 passed / 1 failed).	50.0% passed tests (2 passed / 2 failed).	75.0% passed tests (3 passed / 1 failed).	100.0% passed tests (4 passed / 0 failed).

Change Ccc Low Quality Phone

Threshold: -0.05

Data	Change CCC Low Quality Phone
	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
iemocap-2.3.0-emotion.dimensions.test.gold_standard	-0.10	-0.02	-0.06	-0.04	-0.02
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	-0.24	-0.05	-0.05	-0.04	-0.04
mean	-0.17	-0.04	-0.06	-0.04	-0.03

Percentage Unchanged Predictions Low Quality Phone

Threshold: 0.5

Data	Percentage Unchanged Predictions Low Quality Phone
	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
iemocap-2.3.0-emotion.dimensions.test.gold_standard	0.42	0.64	0.53	0.56	0.53
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	0.29	0.53	0.70	0.40	0.51
mean	0.35	0.58	0.61	0.48	0.52

Visualization

Difference of predictions for original audio and low quality phone audio. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox