Table 1 Male emotion interference matrix by arousal (total accuracy: 96.68%).

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

112

0

1

0

0

98.1%

Normality and fatigue

0

89

1

0

0

95.84%

Disgust

0

0

35

1

0

92.14%

Fear

7

0

1

22

0

74.38%

Discomfort

0

2

0

0

34

84.59%

Accuracy

97.35%

97.70%

89%

96.43%

97.22%

-

Total accuracy: 96.68%