Browse > Article

A Noble Decoding Algorithm Using MLLR Adaptation for Speaker Verification  

김강열 (인하대학교 전자공학과 디지털 신호처리 연구실)
김지운 (인하대학교 전자공학과 디지털 신호처리 연구실)
정재호 (인하대학교 전자공학과 디지털 신호처리 연구실)
Publication Information
The Journal of the Acoustical Society of Korea / v.21, no.2, 2002 , pp. 190-198 More about this Journal
Abstract
In general, we have used the Viterbi algorithm of Speech recognition for decoding. But a decoder in speaker verification has to recognize same word of every speaker differently. In this paper, we propose a noble decoding algorithm that could replace the typical Viterbi algorithm for the speaker verification system. We utilize for the proposed algorithm the speaker adaptation algorithms that transform feature vectors into the region of the client' characteristics in the speech recognition. There are many adaptation algorithms, but we take MLLR (Maximum Likelihood Linear Regression) and MAP (Maximum A-Posterior) adaptation algorithms for proposed algorithm. We could achieve improvement of performance about 30% of EER (Equal Error Rate) using proposed algorithm instead of the typical Viterbi algorithm.
Keywords
Viterbi algorithm; Speaker adaptation; MLLR algorithm; MAP algorithm; Speaker verification;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 /
[ R. O. Duda;P. E. Hart;D. G. Stork ] / Pattern Classification(2nd Edition)
2 Maximum a Poster ori Estimation for Multivariate Gaussian Mixture Observation of Markov Chains /
[ J. L. Gauvian;C. H. Lee ] / IEEE Transactions on Speech and Audio processing   DOI   ScienceOn
3 전화선 채널이 화자확인 시스템의 성능에 미치는 영향 /
[ 조태현;김유진;이재영;정재호 ] / 한국음향학회지   과학기술학회마을
4 A study on speaker adaptation of the parameters of continuous density Hidden Markov Models /
[ C. H. Lee;C. H. Lin ] / IEEE Transactions on signal processing
5 Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm /
[ A. J. Viterbi ] / IEEE Transactions on Information Theory   DOI   ScienceOn
6 Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation /
[ M. J. F. Gales;P. C. Woodland ] / ICSLP 96., Proceedings, Fouth International Conference   DOI
7 Effective speaker adaptations for speaker verification /
[ S. J. Ahn;S. M. Kang;H. S. Ko ] / Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference
8 The 1998 HTK system for transcription of conversational telephone speech /
[ T. Hain;P. C. Woodland;T. R. Niesler;E. W. D. Whittaker ] / Acoustics, Speech, and Signal Processing, 1999. Proceedings, IEEE International Conference
9 Speaker adaptation of HMMs using linear regression /
[ C. J. Leggetter;P. C. Woodland ] / CUED, F-INFENG, TR. 181
10 Iterative unsupervised adaptation using maximum likelihood linear regression /
[ P. C. Woodland;M. J. F. Gales ] / ICSLP 96., Proceedings, Fourth International Conference   DOI
11 On the Viterbi Decoding Algorithm /
[ J. K. Omura ] / IEEE Transactions on Information Theory   DOI