Correctness consistency

18.9% passed tests (7 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

fear

surprise

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

0.36

0.40

danish-emotional-speech-1.1.1-emotion.test

0.44

0.42

emodb-1.2.0-emotion.categories.test.gold_standard

0.36

0.30

emovo-1.2.1-emotion.test

0.43

0.37

0.40

iemocap-2.3.0-emotion.categories.test.gold_standard

0.40

0.41

meld-1.3.1-emotion.categories.test.gold_standard

0.43

0.44

0.35

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

0.45

0.28

ravdess-1.1.2-emotion.speech.test

0.41

0.50

0.31

mean

0.41

0.39

0.37

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

0.41

danish-emotional-speech-1.1.1-emotion.test

0.46

emodb-1.2.0-emotion.categories.test.gold_standard

0.47

0.41

emovo-1.2.1-emotion.test

0.39

iemocap-2.3.0-emotion.categories.test.gold_standard

0.37

meld-1.3.1-emotion.categories.test.gold_standard

0.42

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

0.48

0.15

ravdess-1.1.2-emotion.speech.test

0.59

mean

0.47

0.40

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

0.76

danish-emotional-speech-1.1.1-emotion.test

0.81

emodb-1.2.0-emotion.categories.test.gold_standard

0.74

emovo-1.2.1-emotion.test

0.77

iemocap-2.3.0-emotion.categories.test.gold_standard

0.79

meld-1.3.1-emotion.categories.test.gold_standard

0.80

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

0.78

ravdess-1.1.2-emotion.speech.test

0.88

mean

0.79

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_standard77.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test55.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard55.png
../../../_images/visualization_emovo-1.2.1-emotion.test77.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard77.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard99.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard55.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test55.png