A NEW STUDY OF GMM-SVM SYSTEM FOR TEXT-DEPENDENT SPEAKER RECOGNITION

A NEW STUDY OF GMM-SVM SYSTEM FOR TEXT-DEPENDENT SPEAKER RECOGNITION
Title:
A NEW STUDY OF GMM-SVM SYSTEM FOR TEXT-DEPENDENT SPEAKER RECOGNITION
Other Titles:
40th International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015
DOI:
10.1109/ICASSP.2015.7178761
Publication Date:
19 April 2015
Citation:
H. Sun, K. A. Lee and B. Ma, "A new study of GMM-SVM system for text-dependent speaker recognition," 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, 2015, pp. 4195-4199. doi: 10.1109/ICASSP.2015.7178761
Abstract:
This paper presents a new approach and the study of GMMSVM system for text-dependent speaker recognition on scenario of the fixed pass-phrases. The uniform-split contentbased GMM-SVM system is proposed and applied to textdependent speaker evaluation. We conducted detailed study of the proposed method compared to the baseline GMMSVM 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.
License type:
PublisherCopyrights
Funding Info:
Description:
(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
ISSN:
1520-6149
Files uploaded:

File Size Format Action
hanwu-hlt.pdf 342.60 KB PDF Open