Correctness consistency

30.2% passed tests (13 passed / 30 failed).

Samples In Expected High Range

Proportion of samples whose predictions fall into the expected value range of >= 0.55

Threshold: 0.75

Data

anger

crema-d-1.2.0-emotion.categories.test.gold_standard

0.45

danish-emotional-speech-1.1.1-emotion.test

0.33

emodb-1.2.0-emotion.categories.test.gold_standard

0.36

emovo-1.2.1-emotion.test

0.36

iemocap-2.3.0-emotion.categories.test.gold_standard

0.39

meld-1.3.1-emotion.categories.test.gold_standard

0.40

polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard

0.42

ravdess-1.1.2-emotion.speech.test

0.47

mean

0.40

Samples In Expected Low Range

Proportion of samples whose predictions fall into the expected value range of <= 0.45

Threshold: 0.75

Data

fear

sadness

crema-d-1.2.0-emotion.categories.test.gold_standard

0.37

0.49

danish-emotional-speech-1.1.1-emotion.test

0.58

emodb-1.2.0-emotion.categories.test.gold_standard

0.33

0.56

emovo-1.2.1-emotion.test

0.38

0.32

iemocap-2.3.0-emotion.categories.test.gold_standard

0.29

0.37

meld-1.3.1-emotion.categories.test.gold_standard

0.38

0.42

polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard

0.38

0.48

ravdess-1.1.2-emotion.speech.test

0.38

0.41

mean

0.36

0.45

Samples In Expected Neutral Range

Proportion of samples whose predictions fall into the expected value range of [0.3, 0.6]

Threshold: 0.75

Data

happiness

neutral

surprise

crema-d-1.2.0-emotion.categories.test.gold_standard

0.73

0.79

danish-emotional-speech-1.1.1-emotion.test

0.77

0.73

0.81

emodb-1.2.0-emotion.categories.test.gold_standard

0.81

0.70

emovo-1.2.1-emotion.test

0.77

0.73

0.76

iemocap-2.3.0-emotion.categories.test.gold_standard

0.80

0.76

meld-1.3.1-emotion.categories.test.gold_standard

0.80

0.79

0.81

polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard

0.75

0.90

ravdess-1.1.2-emotion.speech.test

0.75

0.75

0.88

mean

0.77

0.77

0.81

Visualization

Distribution of dimensional model predictions for samples with different categorical emotions. The expected range of model predictions is highlighted by the green brackground.

../../../_images/visualization_crema-d-1.2.0-emotion.categories.test.gold_standard78.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test56.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard56.png
../../../_images/visualization_emovo-1.2.1-emotion.test78.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard78.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard100.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard56.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test56.png