Correctness classification

66.0% passed tests (66 passed / 34 failed).

Precision Per Class

Threshold: 0.5

Data

anger

happiness

neutral

sadness

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

0.62

0.47

0.90

0.10

danish-emotional-speech-1.1.1-emotion.test

0.64

0.68

0.34

0.41

emodb-1.2.0-emotion.categories.test.gold_standard

0.77

0.90

0.74

0.95

emovo-1.2.1-emotion.test

0.70

0.81

0.46

0.86

iemocap-2.3.0-emotion.categories.test.gold_standard

0.82

0.28

0.69

0.55

meld-1.3.1-emotion.categories.test.gold_standard

0.42

0.24

0.74

0.29

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

0.43

0.70

0.82

0.27

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

0.17

0.60

0.74

0.18

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

0.81

0.67

0.51

1.00

ravdess-1.1.2-emotion.speech.test

0.79

0.67

0.30

0.51

mean

0.62

0.60

0.62

0.51

Recall Per Class

Threshold: 0.5

Data

anger

happiness

neutral

sadness

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

0.74

0.37

0.34

0.89

danish-emotional-speech-1.1.1-emotion.test

0.27

0.44

0.75

0.29

emodb-1.2.0-emotion.categories.test.gold_standard

0.98

0.33

0.96

0.74

emovo-1.2.1-emotion.test

0.83

0.26

0.94

0.38

iemocap-2.3.0-emotion.categories.test.gold_standard

0.66

0.62

0.39

0.72

meld-1.3.1-emotion.categories.test.gold_standard

0.51

0.73

0.19

0.37

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

0.73

0.78

0.57

0.57

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

0.53

0.48

0.67

0.36

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

0.55

0.85

0.95

0.18

ravdess-1.1.2-emotion.speech.test

0.81

0.06

0.50

0.78

mean

0.66

0.49

0.63

0.53

Unweighted Average Precision

Threshold: 0.5

Data

Unweighted Average Precision

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

0.52

danish-emotional-speech-1.1.1-emotion.test

0.51

emodb-1.2.0-emotion.categories.test.gold_standard

0.84

emovo-1.2.1-emotion.test

0.71

iemocap-2.3.0-emotion.categories.test.gold_standard

0.58

meld-1.3.1-emotion.categories.test.gold_standard

0.42

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

0.55

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

0.42

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

0.75

ravdess-1.1.2-emotion.speech.test

0.57

mean

0.59

Unweighted Average Recall

Threshold: 0.5

Data

Unweighted Average Recall

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

0.58

danish-emotional-speech-1.1.1-emotion.test

0.44

emodb-1.2.0-emotion.categories.test.gold_standard

0.75

emovo-1.2.1-emotion.test

0.60

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

0.66

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

0.51

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

0.63

ravdess-1.1.2-emotion.speech.test

0.54

mean

0.58

Visualization

../../../_images/visualization_crema-d-1.2.0-emotion.categories.test.gold_standard24.png
../../../_images/visualization_danish-emotional-speech-1.1.1-emotion.test24.png
../../../_images/visualization_emodb-1.2.0-emotion.categories.test.gold_standard24.png
../../../_images/visualization_emovo-1.2.1-emotion.test24.png
../../../_images/visualization_iemocap-2.3.0-emotion.categories.test.gold_standard24.png
../../../_images/visualization_meld-1.3.1-emotion.categories.test.gold_standard24.png
../../../_images/visualization_msppodcast-2.6.0-emotion.categories.test-1.gold_standard2.png
../../../_images/visualization_msppodcast-2.6.0-emotion.categories.test-2.gold_standard2.png
../../../_images/visualization_polish-emotional-speech-1.1.1-emotion.categories.test.gold_standard24.png
../../../_images/visualization_ravdess-1.1.2-emotion.speech.test24.png