Robustness simulated recording condition¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
|---|---|---|---|---|
Overall Score |
16.7% passed tests (1 passed / 5 failed). |
16.7% passed tests (1 passed / 5 failed). |
50.0% passed tests (3 passed / 3 failed). |
16.7% passed tests (1 passed / 5 failed). |
Percentage Unchanged Predictions Simulated Position¶
Data |
Percentage Unchanged Predictions Simulated Position |
|||
|---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
emovo-1.2.1-emotion.test |
0.60 |
0.75 |
0.83 |
0.59 |
imda-nsc-read-speech-balanced-2.6.0-headset |
0.78 |
0.79 |
0.90 |
0.73 |
timit-1.4.1-files |
0.87 |
0.86 |
0.94 |
0.83 |
mean |
0.75 |
0.80 |
0.89 |
0.72 |
Percentage Unchanged Predictions Simulated Room¶
Data |
Percentage Unchanged Predictions Simulated Room |
|||
|---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
emovo-1.2.1-emotion.test |
0.42 |
0.67 |
0.72 |
0.45 |
imda-nsc-read-speech-balanced-2.6.0-headset |
0.56 |
0.80 |
0.61 |
0.53 |
timit-1.4.1-files |
0.68 |
0.77 |
0.54 |
0.65 |
mean |
0.55 |
0.75 |
0.62 |
0.54 |
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.
w2v2-L |
hubert-L |
wavlm |
data2vec |
|---|---|---|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|