Robustness simulated recording condition¶
CNN14 |
w2v2-b |
hubert-b |
axlstm |
|
---|---|---|---|---|
Overall Score |
0.0% passed tests (0 passed / 6 failed). |
0.0% passed tests (0 passed / 6 failed). |
0.0% passed tests (0 passed / 6 failed). |
0.0% passed tests (0 passed / 6 failed). |
Percentage Unchanged Predictions Simulated Position¶
Data |
Percentage Unchanged Predictions Simulated Position |
|||
---|---|---|---|---|
CNN14 |
w2v2-b |
hubert-b |
axlstm |
|
emovo-1.2.1-emotion.test |
0.35 |
0.59 |
0.50 |
0.52 |
imda-nsc-read-speech-balanced-2.6.0-headset |
0.54 |
0.62 |
0.66 |
0.56 |
timit-1.4.1-files |
0.39 |
0.57 |
0.60 |
0.47 |
mean |
0.43 |
0.59 |
0.59 |
0.52 |
Percentage Unchanged Predictions Simulated Room¶
Data |
Percentage Unchanged Predictions Simulated Room |
|||
---|---|---|---|---|
CNN14 |
w2v2-b |
hubert-b |
axlstm |
|
emovo-1.2.1-emotion.test |
0.26 |
0.52 |
0.40 |
0.39 |
imda-nsc-read-speech-balanced-2.6.0-headset |
0.34 |
0.55 |
0.57 |
0.36 |
timit-1.4.1-files |
0.30 |
0.49 |
0.45 |
0.29 |
mean |
0.30 |
0.52 |
0.47 |
0.35 |
Visualization Simulated Position¶
Difference of predictions for audio with a baseline simulated position and audio with a different simulated position. 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.
CNN14 |
w2v2-b |
hubert-b |
axlstm |
---|---|---|---|