Correctness consistency

64.9% passed tests (24 passed / 13 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

0.82

0.41

danish-emotional-speech-1.1.1-emotion.test

0.46

0.37

emodb-1.2.0-emotion.categories.test.gold_standard

1.00

0.94

emovo-1.2.1-emotion.test

0.96

0.55

0.60

iemocap-2.3.0-emotion.categories.test.gold_standard

0.87

0.59

meld-1.3.1-emotion.categories.test.gold_standard

0.96

0.86

0.81

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

0.95

0.35

ravdess-1.1.2-emotion.speech.test

0.91

0.50

0.97

mean

0.87

0.60

0.69

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

0.85

danish-emotional-speech-1.1.1-emotion.test

1.00

emodb-1.2.0-emotion.categories.test.gold_standard

0.97

1.00

emovo-1.2.1-emotion.test

0.88

iemocap-2.3.0-emotion.categories.test.gold_standard

0.84

meld-1.3.1-emotion.categories.test.gold_standard

0.24

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

1.00

1.00

ravdess-1.1.2-emotion.speech.test

0.84

mean

0.98

0.83

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

0.51

danish-emotional-speech-1.1.1-emotion.test

0.54

emodb-1.2.0-emotion.categories.test.gold_standard

0.96

emovo-1.2.1-emotion.test

0.90

iemocap-2.3.0-emotion.categories.test.gold_standard

0.81

meld-1.3.1-emotion.categories.test.gold_standard

0.72

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

0.98

ravdess-1.1.2-emotion.speech.test

0.50

mean

0.74

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_standard5.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test5.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard5.png
../../../_images/visualization_emovo-1.2.1-emotion.test5.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard5.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard5.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard5.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test5.png