Correctness classification

64.0% passed tests (64 passed / 36 failed).

Precision Per Class

Threshold: 0.5

Data

anger

happiness

neutral

sadness

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

0.53

0.33

0.87

0.15

danish-emotional-speech-1.1.1-emotion.test

0.62

0.68

0.33

0.55

emodb-1.2.0-emotion.categories.test.gold_standard

0.68

0.50

0.75

0.90

emovo-1.2.1-emotion.test

0.54

0.86

0.47

0.97

iemocap-2.3.0-emotion.categories.test.gold_standard

0.79

0.33

0.67

0.56

meld-1.3.1-emotion.categories.test.gold_standard

0.40

0.25

0.77

0.33

msppodcast-2.6.0-emotion.categories.test-1.gold_standard

0.42

0.75

0.78

0.24

msppodcast-2.6.0-emotion.categories.test-2.gold_standard

0.18

0.63

0.72

0.20

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

0.67

0.58

0.45

1.00

ravdess-1.1.2-emotion.speech.test

0.62

0.00

0.24

0.70

mean

0.55

0.49

0.60

0.56

Recall Per Class

Threshold: 0.5

Data

anger

happiness

neutral

sadness

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

0.65

0.25

0.59

0.72

danish-emotional-speech-1.1.1-emotion.test

0.29

0.29

0.83

0.33

emodb-1.2.0-emotion.categories.test.gold_standard

0.98

0.07

0.89

0.70

emovo-1.2.1-emotion.test

0.87

0.14

0.89

0.33

iemocap-2.3.0-emotion.categories.test.gold_standard

0.66

0.54

0.52

0.68

meld-1.3.1-emotion.categories.test.gold_standard

0.47

0.73

0.25

0.35

msppodcast-2.6.0-emotion.categories.test-1.gold_standard

0.73

0.69

0.65

0.51

msppodcast-2.6.0-emotion.categories.test-2.gold_standard

0.55

0.41

0.74

0.36

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

0.65

0.55

0.82

0.22

ravdess-1.1.2-emotion.speech.test

0.88

0.00

0.56

0.59

mean

0.67

0.37

0.67

0.48

Unweighted Average Precision

Threshold: 0.5

Data

Unweighted Average Precision

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

0.47

danish-emotional-speech-1.1.1-emotion.test

0.55

emodb-1.2.0-emotion.categories.test.gold_standard

0.71

emovo-1.2.1-emotion.test

0.71

iemocap-2.3.0-emotion.categories.test.gold_standard

0.59

meld-1.3.1-emotion.categories.test.gold_standard

0.44

msppodcast-2.6.0-emotion.categories.test-1.gold_standard

0.55

msppodcast-2.6.0-emotion.categories.test-2.gold_standard

0.43

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

0.67

ravdess-1.1.2-emotion.speech.test

0.39

mean

0.55

Unweighted Average Recall

Threshold: 0.5

Data

Unweighted Average Recall

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

0.55

danish-emotional-speech-1.1.1-emotion.test

0.43

emodb-1.2.0-emotion.categories.test.gold_standard

0.66

emovo-1.2.1-emotion.test

0.56

iemocap-2.3.0-emotion.categories.test.gold_standard

0.60

meld-1.3.1-emotion.categories.test.gold_standard

0.45

msppodcast-2.6.0-emotion.categories.test-1.gold_standard

0.65

msppodcast-2.6.0-emotion.categories.test-2.gold_standard

0.51

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

0.56

ravdess-1.1.2-emotion.speech.test

0.51

mean

0.55

Visualization

../../../_images/visualization_crema-d-1.2.0-emotion.categories.test.gold_standard54.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test38.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard38.png
../../../_images/visualization_emovo-1.2.1-emotion.test54.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard54.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard70.png
../../../_images/visualization_msppodcast-2.6.0-emotion.categories.test-1.gold_standard48.png
../../../_images/visualization_msppodcast-2.6.0-emotion.categories.test-2.gold_standard16.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard38.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test38.png