Table 2 Female emotion interference matrix by arousal (total accuracy: 88.03%).

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

Feeling

Anger and happiness

Normality and fatigue

Disgust

Fear

Discomfort

Detection rate (%)

Anger and happiness

79

0

0

8

0

90.80%

Normality and fatigue

1

69

0

0

4

93.24%

Disgust

1

2

7

1

0

63.64%

Fear

7

1

0

29

0

78.38%

Discomfort

0

3

0

0

22

88.00%

Accuracy

89.77%

92%

100%

76.32%

84.62%

-

Total accuracy: 88.03%