Robustness low quality phone¶
w2v2-L-cat |
hubert-L-cat |
wavlm-cat |
data2vec-cat |
|
---|---|---|---|---|
Overall Score |
90.0% passed tests (9 passed / 1 failed). |
80.0% passed tests (8 passed / 2 failed). |
90.0% passed tests (9 passed / 1 failed). |
90.0% passed tests (9 passed / 1 failed). |
Change Uar Low Quality Phone¶
Data |
Change UAR Low Quality Phone |
|||
---|---|---|---|---|
w2v2-L-cat |
hubert-L-cat |
wavlm-cat |
data2vec-cat |
|
crema-d-1.2.0-emotion.categories.test.gold_standard |
-0.10 |
-0.10 |
-0.09 |
-0.06 |
emovo-1.2.1-emotion.test |
0.01 |
-0.02 |
-0.01 |
0.05 |
iemocap-2.3.0-emotion.categories.test.gold_standard |
-0.02 |
-0.03 |
-0.03 |
-0.03 |
meld-1.3.1-emotion.categories.test.gold_standard |
-0.01 |
-0.01 |
-0.01 |
-0.00 |
msppodcast-2.6.0-emotion.categories.test-1.gold_standard |
-0.02 |
-0.05 |
-0.01 |
-0.03 |
mean |
-0.03 |
-0.04 |
-0.03 |
-0.01 |
Percentage Unchanged Predictions Low Quality Phone¶
Data |
Percentage Unchanged Predictions Low Quality Phone |
|||
---|---|---|---|---|
w2v2-L-cat |
hubert-L-cat |
wavlm-cat |
data2vec-cat |
|
crema-d-1.2.0-emotion.categories.test.gold_standard |
0.71 |
0.75 |
0.75 |
0.68 |
emovo-1.2.1-emotion.test |
0.72 |
0.74 |
0.81 |
0.69 |
iemocap-2.3.0-emotion.categories.test.gold_standard |
0.77 |
0.78 |
0.81 |
0.76 |
meld-1.3.1-emotion.categories.test.gold_standard |
0.74 |
0.70 |
0.78 |
0.69 |
msppodcast-2.6.0-emotion.categories.test-1.gold_standard |
0.70 |
0.79 |
0.83 |
0.76 |
mean |
0.73 |
0.75 |
0.80 |
0.72 |
Visualization¶
Confusion Matrix showing the shift from the predictions of the original audio to the predictions of the low quality phone audio.
w2v2-L-cat |
hubert-L-cat |
wavlm-cat |
data2vec-cat |
---|---|---|---|