Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 15 Emotion recognition rates of decision tree SVM with parameter optimization and feature selection (EMO-DB) (%)

From: Decision tree SVM model with Fisher feature selection for speech emotion recognition

Emotions

Angry

Happy

Fear

Neutral

Boring

Sad

Disgust

Angry

91.8

3.4

1.2

0.25

0.9

0.8

1.65

Happy

6.4

85

5.5

0.24

0.82

0.5

1.54

Fear

3.5

2.74

88.3

0.42

1.8

2.01

1.23

Neutral

1.2

2.75

0.81

94.5

0.14

0.3

0.2

Boring

2.1

1.85

1.74

0.9

89.85

1.85

1.71

Sad

0.57

1.5

2.4

1.5

8.4

83

2.45

Disgust

5.5

4.75

4.2

1.2

1.5

2.4

80.45

Average recognition rate

 

87.55

    
Back to article page