TY - GEN
T1 - A new study of GMM-SVM system for text-dependent speaker recognition
AU - Sun, Hanwu
AU - Lee, Kong Aik
AU - Ma, Bin
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/8/4
Y1 - 2015/8/4
N2 - This paper presents a new approach and the study of GMM-SVM system for text-dependent speaker recognition on scenario of the fixed pass-phrases. The uniform-split content-based GMM-SVM system is proposed and applied to text-dependent speaker evaluation. We conducted detailed study of the proposed method compared to the baseline GMM-SVM system on the RSR2015 database, which has been designed and collected for the evaluation of text-dependent speaker verification system. The experiment results show that the new approach can significantly reduce the detection error of the target-wrong error type (i.e., target speaker with wrong pass-phrase) while maintaining a low detection error for both imposter-correct and imposter-wrong error types (i.e., imposter with correct pass-phrase and imposter with wrong pass-phrase). We also show that score normalization could be applied with respect to the imposter-wrong distribution as opposed to the imposter-correct distribution.
AB - This paper presents a new approach and the study of GMM-SVM system for text-dependent speaker recognition on scenario of the fixed pass-phrases. The uniform-split content-based GMM-SVM system is proposed and applied to text-dependent speaker evaluation. We conducted detailed study of the proposed method compared to the baseline GMM-SVM system on the RSR2015 database, which has been designed and collected for the evaluation of text-dependent speaker verification system. The experiment results show that the new approach can significantly reduce the detection error of the target-wrong error type (i.e., target speaker with wrong pass-phrase) while maintaining a low detection error for both imposter-correct and imposter-wrong error types (i.e., imposter with correct pass-phrase and imposter with wrong pass-phrase). We also show that score normalization could be applied with respect to the imposter-wrong distribution as opposed to the imposter-correct distribution.
KW - channel compensation
KW - speaker recognition
KW - text dependent
UR - http://www.scopus.com/inward/record.url?scp=84946077642&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2015.7178761
DO - 10.1109/ICASSP.2015.7178761
M3 - Conference article published in proceeding or book
AN - SCOPUS:84946077642
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4195
EP - 4199
BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Y2 - 19 April 2014 through 24 April 2014
ER -