Correctness consistency

59.5% passed tests (22 passed / 15 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

fear

surprise

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

0.80

0.39

danish-emotional-speech-1.1.1-emotion.test

0.42

0.13

emodb-1.2.0-emotion.categories.test.gold_standard

1.00

1.00

emovo-1.2.1-emotion.test

0.88

0.38

0.49

iemocap-2.3.0-emotion.categories.test.gold_standard

0.74

0.35

meld-1.3.1-emotion.categories.test.gold_standard

0.90

0.80

0.71

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

0.92

0.40

ravdess-1.1.2-emotion.speech.test

0.81

0.47

0.94

mean

0.81

0.54

0.57

Samples In Expected Low Range

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

Threshold: 0.75

Data

boredom

sadness

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

0.95

danish-emotional-speech-1.1.1-emotion.test

1.00

emodb-1.2.0-emotion.categories.test.gold_standard

0.81

1.00

emovo-1.2.1-emotion.test

1.00

iemocap-2.3.0-emotion.categories.test.gold_standard

0.91

meld-1.3.1-emotion.categories.test.gold_standard

0.35

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

0.98

1.00

ravdess-1.1.2-emotion.speech.test

0.88

mean

0.90

0.89

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

neutral

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

0.45

danish-emotional-speech-1.1.1-emotion.test

0.54

emodb-1.2.0-emotion.categories.test.gold_standard

1.00

emovo-1.2.1-emotion.test

0.77

iemocap-2.3.0-emotion.categories.test.gold_standard

0.64

meld-1.3.1-emotion.categories.test.gold_standard

0.79

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

0.82

ravdess-1.1.2-emotion.speech.test

0.44

mean

0.68

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_standard9.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test9.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard9.png
../../../_images/visualization_emovo-1.2.1-emotion.test9.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard9.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard9.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard9.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test9.png