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

Table 12 Comparison of emotion classification mean error rate values for different lengths of the feature vector

From: Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Feature vector length/emotion

Mean error rate (%)

 

Neutral

Joy

Sadness

Anger

NFEAT = 8

35.38

50.68

47.89

63.42

NFEAT = 16

20.51

33.71

11.14

43.19

NFEAT = 32

15.82

34.66

12.46

33.04

Back to article page