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

0.79

0.40

danish-emotional-speech-1.1.1-emotion.test

0.33

0.27

emodb-1.2.0-emotion.categories.test.gold_standard

1.00

0.79

emovo-1.2.1-emotion.test

0.89

0.42

0.58

iemocap-2.3.0-emotion.categories.test.gold_standard

0.82

0.65

meld-1.3.1-emotion.categories.test.gold_standard

0.96

0.94

0.85

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

0.95

0.42

ravdess-1.1.2-emotion.speech.test

0.97

0.44

1.00

mean

0.84

0.58

0.68

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

0.87

danish-emotional-speech-1.1.1-emotion.test

1.00

emodb-1.2.0-emotion.categories.test.gold_standard

0.92

1.00

emovo-1.2.1-emotion.test

0.93

iemocap-2.3.0-emotion.categories.test.gold_standard

0.84

meld-1.3.1-emotion.categories.test.gold_standard

0.19

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

0.95

0.98

ravdess-1.1.2-emotion.speech.test

0.84

mean

0.94

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

0.61

danish-emotional-speech-1.1.1-emotion.test

0.37

emodb-1.2.0-emotion.categories.test.gold_standard

0.78

emovo-1.2.1-emotion.test

0.82

iemocap-2.3.0-emotion.categories.test.gold_standard

0.78

meld-1.3.1-emotion.categories.test.gold_standard

0.45

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

0.92

ravdess-1.1.2-emotion.speech.test

0.06

mean

0.60

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_standard2.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test2.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard2.png
../../../_images/visualization_emovo-1.2.1-emotion.test2.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard2.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard2.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard2.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test2.png