Robustness spectral tilt

Overall scores

	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
Overall Score	87.5% passed tests (7 passed / 1 failed).	87.5% passed tests (7 passed / 1 failed).	100.0% passed tests (8 passed / 0 failed).	87.5% passed tests (7 passed / 1 failed).	75.0% passed tests (6 passed / 2 failed).

Change Ccc Downward Tilt

Threshold: -0.05

Data	Change CCC Downward Tilt
	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
iemocap-2.3.0-emotion.dimensions.test.gold_standard	-0.01	-0.01	-0.00	-0.01	-0.01
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	0.00	0.00	0.01	-0.00	-0.00
mean	-0.01	-0.01	0.01	-0.01	-0.01

Change Ccc Upward Tilt

Threshold: -0.05

Data	Change CCC Upward Tilt
	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
iemocap-2.3.0-emotion.dimensions.test.gold_standard	-0.02	-0.02	-0.03	-0.02	-0.01
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	-0.02	-0.02	-0.02	-0.02	-0.04
mean	-0.02	-0.02	-0.03	-0.02	-0.03

Percentage Unchanged Predictions Downward Tilt

Threshold: 0.8

Data	Percentage Unchanged Predictions Downward Tilt
	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
iemocap-2.3.0-emotion.dimensions.test.gold_standard	0.99	0.99	1.00	1.00	0.99
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	1.00	0.99	0.99	0.99	0.98
mean	0.99	0.99	0.99	0.99	0.98

Percentage Unchanged Predictions Upward Tilt

Threshold: 0.8

Data	Percentage Unchanged Predictions Upward Tilt
	w2v2-b	w2v2-L	w2v2-L-robust	w2v2-L-xls-r	w2v2-L-vox
iemocap-2.3.0-emotion.dimensions.test.gold_standard	0.75	0.73	0.85	0.82	0.69
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard	0.90	0.88	0.90	0.80	0.70
mean	0.82	0.80	0.88	0.81	0.69

Visualization Downward Tilt

Difference of predictions for original audio and audio with a downward spectral tilt. 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