Skip to main content

Table 1 Speaker identification error rates (%) by ML-GMM, MCE-GMM, SVM, and the proposed DSW-GMM

From: Discriminative likelihood score weighting based on acoustic-phonetic classification for speaker identification

SNR

ML-GMM

MCE-GMM (mixture weights only)

SVM

DSW-GMM

Error reduction over ML-GMM

Clean

10.90

10.90

9.00

8.30

23.85

20 dB

17.70

17.05

25.43

15.80

10.73

10 dB

30.02

29.35

42.45

26.45

11.89

0 dB

72.13

68.53

69.53

59.22

17.90