Browse > Article

Speaker Verification Using Hidden LMS Adaptive Filtering Algorithm and Competitive Learning Neural Network  

Cho, Seong-Won (홍익대 전기전자공학부)
Kim, Jae-Min (홍익대 전기전자공학부)
Publication Information
The Transactions of the Korean Institute of Electrical Engineers D / v.51, no.2, 2002 , pp. 69-77 More about this Journal
Abstract
Speaker verification can be classified in two categories, text-dependent speaker verification and text-independent speaker verification. In this paper, we discuss text-dependent speaker verification. Text-dependent speaker verification system determines whether the sound characteristics of the speaker are equal to those of the specific person or not. In this paper we obtain the speaker data using a sound card in various noisy conditions, apply a new Hidden LMS (Least Mean Square) adaptive algorithm to it, and extract LPC (Linear Predictive Coding)-cepstrum coefficients as feature vectors. Finally, we use a competitive learning neural network for speaker verification. The proposed hidden LMS adaptive filter using a neural network reduces noise and enhances features in various noisy conditions. We construct a separate neural network for each speaker, which makes it unnecessary to train the whole network for a new added speaker and makes the system expansion easy. We experimentally prove that the proposed method improves the speaker verification performance.
Keywords
speaker verification; Hidden LMS adaptive algorithm; neural network;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Philip D. Wasserman, 'Neural Computing', Van Nostrand Reinhold, 1989
2 Benjamin Miller, 'Vital Signs of Identity', IEEE Spectrum Special Report pp.22-30
3 L.B.Rabiner and R.W.Schafer, Digital Processing of Speech Signals, Prentice Hall, New Jersey, 1978
4 강문기, '일반화된 성도모델에 기반을 둔 선형예측기법', 석사학위논문, 서울대학교 공과대학, 1998
5 C.F.N. Cowan & P.M. Grant 'Addative Filters', Prentice-Hal, New Jersey, 1985
6 이인홍, '잡음이 섞인 신호를 개선하기 위한 LMS 적용 필터링에 관한 연구', 석사학위논문, 광운대학교 대학원, 1987
7 D.K.Burton, 'Text-Dependent Speaker Verification Using Vector Quantization Source Coding', IEEE Trans. on ASSP vol. 35, pp.133-143   DOI
8 한국과학재단, '음성처리 및 인식의 기초연구', 1989
9 R.W.Hamming, 'Digital Filters', Prentice-Hall, New Jersey, 1989
10 L.Rabiner, Biing-Hwang Juang, 'Fundamentals of Speech Recognition', Prentice-Hall, New Jersey, 1993
11 Laurene Fausett, 'Fundamentals of Neural Network', Prentice Hall, 1994
12 S.Furui, 'Cepstral analysis technique for automatic speaker verification', IEEE Trans. on ASSP, vol. 29, pp.254-272   DOI
13 F.K.Soong, A.Aron E. Rosenberg, 'On the Use of Instantaneous and Transitional Spectral Information in Speaker Recognition', IEEE Trans. on ASSP, vol. 36, pp.871-879   DOI   ScienceOn