Correctness speaker average

Overall scores

CNN14

w2v2-b

hubert-b

axlstm

Overall Score

100.0% passed tests (3 passed / 0 failed).

100.0% passed tests (3 passed / 0 failed).

100.0% passed tests (3 passed / 0 failed).

100.0% passed tests (3 passed / 0 failed).

Mean Absolute Error

Threshold: 0.1

Data

Mean Absolute Error

CNN14

w2v2-b

hubert-b

axlstm

iemocap-2.3.0-full

0.05

0.04

0.05

0.04

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.04

0.04

0.03

0.03

msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard

0.05

0.05

0.04

0.02

mean

0.05

0.04

0.04

0.03

Visualization

The plot shows the predicted average value with the true average value. We select a slightly higher threshold for the absolute error in the plots compared to the Mean Absolute Error test as we are interested in highlighting only big deviations here.

CNN14

w2v2-b

hubert-b

axlstm

../../../_images/visualization_iemocap-2.3.0-full11.png
../../../_images/visualization_iemocap-2.3.0-full12.png
../../../_images/visualization_iemocap-2.3.0-full13.png
../../../_images/visualization_iemocap-2.3.0-full14.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard74.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard75.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard76.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard77.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard52.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard53.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard54.png
../../../_images/visualization_msppodcast-2.6.1-emotion.dimensions.test-2.gold_standard55.png