Table 5 Male 7-emotion interference matrix (total accuracy: 96.35%).

From: A deep learning framework for gender sensitive speech emotion recognition based on MFCC feature selection and SHAP analysis

Emotion

Anger

Happiness

Fatigue

Neutral

Disgust

Fear

Sadness

Recognition Rate (%)

Anger

66

0

0

1

0

0

0

98.51

Happiness

1

43

0

0

0

0

0

97.73

Fatigue

0

0

45

0

1

0

0

97.83

Neutral

0

0

0

40

0

0

0

100

Disgust

0

0

0

0

34

1

0

97.14

Fear

3

0

0

0

1

27

1

84.38

Sadness

0

0

1

1

0

0

35

94.59

Precision (%)

94.29

100

97.83

97.56

91.89

94.43

97.22

-

  

Total accuracy: 96.35%