Robustness recording condition

Overall scores

w2v2-b

w2v2-L

w2v2-L-robust

w2v2-L-xls-r

w2v2-L-vox

Overall Score

0.0% passed tests (0 passed / 2 failed).

0.0% passed tests (0 passed / 2 failed).

50.0% passed tests (1 passed / 1 failed).

0.0% passed tests (0 passed / 2 failed).

0.0% passed tests (0 passed / 2 failed).

Percentage Unchanged Predictions Recording Condition

Threshold: 0.8

Data

Percentage Unchanged Predictions Recording Condition

w2v2-b

w2v2-L

w2v2-L-robust

w2v2-L-xls-r

w2v2-L-vox

imda-nsc-read-speech-balanced-2.6.0-headset-boundary

0.72

0.71

0.87

0.56

0.66

imda-nsc-read-speech-balanced-2.6.0-headset-mobile

0.56

0.57

0.77

0.42

0.51

mean

0.64

0.64

0.82

0.49

0.58

Visualization

Difference of predictions for baseline recording condition audio and different recording condition 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

../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-boundary34.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-boundary37.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-boundary38.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-boundary39.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-boundary40.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-mobile34.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-mobile37.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-mobile38.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-mobile39.png
../../../_images/visualization_imda-nsc-read-speech-balanced-2.6.0-headset-mobile40.png