Robustness spectral tilt¶
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
---|---|---|---|---|
Overall Score |
75.0% passed tests (6 passed / 2 failed). |
100.0% passed tests (8 passed / 0 failed). |
100.0% passed tests (8 passed / 0 failed). |
100.0% passed tests (8 passed / 0 failed). |
Change Ccc Downward Tilt¶
Data |
Change CCC Downward Tilt |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
-0.01 |
-0.01 |
-0.01 |
-0.02 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
-0.00 |
-0.01 |
-0.02 |
-0.01 |
mean |
-0.01 |
-0.01 |
-0.01 |
-0.01 |
Change Ccc Upward Tilt¶
Data |
Change CCC Upward Tilt |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.01 |
-0.00 |
-0.00 |
0.02 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
-0.00 |
-0.00 |
-0.00 |
-0.01 |
mean |
0.01 |
0.00 |
0.00 |
0.01 |
Percentage Unchanged Predictions Downward Tilt¶
Data |
Percentage Unchanged Predictions Downward Tilt |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.94 |
0.99 |
0.98 |
0.96 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.90 |
0.95 |
0.92 |
0.94 |
mean |
0.92 |
0.97 |
0.95 |
0.95 |
Percentage Unchanged Predictions Upward Tilt¶
Data |
Percentage Unchanged Predictions Upward Tilt |
|||
---|---|---|---|---|
w2v2-L |
hubert-L |
wavlm |
data2vec |
|
iemocap-2.3.0-emotion.dimensions.test.gold_standard |
0.59 |
0.85 |
0.84 |
0.82 |
msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard |
0.72 |
0.93 |
0.83 |
0.81 |
mean |
0.66 |
0.89 |
0.83 |
0.81 |
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-L |
hubert-L |
wavlm |
data2vec |
---|---|---|---|