Journal of KIISE:Software and Applications (한국정보과학회논문지:소프트웨어및응용)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Robust Speaker Identification using Independent Component Analysis

독립성분 분석을 이용한 강인한 화자식별

  • 장길진 (한국과학기술원 전산학과) ;
  • 오영환 (한국과학기술원 전산학과)
  • Published : 2000.05.15
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes feature parameter transformation method using independent component analysis (ICA) for speaker identification. The proposed method assumes that the cepstral vectors from various channel-conditioned speech are constructed by a linear combination of some characteristic functions with random channel noise added, and transforms them into new vectors using ICA. The resultant vector space can give emphasis to the repetitive speaker information and suppress the random channel distortions. Experimental results show that the transformation method is effective for the improvement of speaker identification system.

본 논문에서는 독립성분분석을 이용한 음성의 특징 벡터 변환방법을 제안한다. 제안한 방법은 여러 환경에서 수집된 음성신호의 켑스트럼 벡터를 다수의 특징 함수들의 선형결합으로 가정하고, 독립성분분석을 이용하여 분리된 켑스트럼 벡터를 학습과 인식에 사용한다. 변환된 벡터 영역에서는 반복적으로 나타나는 화자의 특징 정보는 강조되고 임의로 나타나는 채널 왜곡은 억제되는 효과를 볼 수 있다. 제안된 방법의 유효성을 검증하기 위해 실제 전화음성으로 문장독립형 화자식별 실험을 수행하였으며, 결과를 통해 독립성분분석을 이용한 특징벡터의 변환이 채널 환경 변화에 대해 보다 강인함을 보였다.

Keywords

References

  1. J. P. Campbell, Jr., 'Speaker recognition: a tutorial,' Proceedings of the IEEE, vol.85, pp.1436-1462, 1997 https://doi.org/10.1109/5.628714
  2. J. de Veth and H. Bourlard, 'Comparison of Hidden Markov Model techniques for automatic speaker verification in real-world conditions,' Speech Communications, vol.17, pp.81-90, 1995 https://doi.org/10.1016/0167-6393(95)00015-G
  3. A. E. Rogenberg, C.-H. Lee, and F. K. Soong, 'Cepstral channel normalization techniques for HMM based speaker verification,' in Proceedings of ICSLP, Yokohama, pp.1835-1838, 1994
  4. M. G. Rahim and B.-H. Juang, 'Signal bias removal by maximum likelihood estimation for robust telephone speech recognition,' IEEE Trans. on Speech and Audio Processing, vol.4, pp.16-30, 1996 https://doi.org/10.1109/TSA.1996.481449
  5. R.J. Mammone, X. Zhang, and R. P. Ramachandran, 'Robust speaker recognition: a feature-based approach,' IEEE signal processing magazaine, pp.58-71, 1996 https://doi.org/10.1109/79.536825
  6. P. Comon, 'Independent component analysis, A new concept?' Signal Processing, vol.36, pp.287-314, 1994 https://doi.org/10.1016/0165-1684(94)90029-9
  7. K. J. Pope and R. E. Bogner, 'Blind signal separation: linear, instaneous combinations,' Digital signal processing, pp.5-16, 1996 https://doi.org/10.1006/dspr.1996.0002
  8. T.-W. Lee, A. Ziehe, R. Orglmeister, and T. Sejnowski, 'Combining time-delayed decorrelation and ICA: towards solving the cocktail party problem,' in Proceedings of ICASSP, pp.1249-1252, 1998 https://doi.org/10.1109/ICASSP.1998.675498
  9. A. Hyvaerinen, 'A family of fixed-point algorithms for independent component analysis,' in Proceedings of ICASSP, pp.3917-3920, 1997 https://doi.org/10.1109/ICASSP.1997.604766
  10. A. Hyvaerinen, 'Independent component analysis by minimization of mutual information,' Technical Report A46, Helsinki University of Technology, 1997
  11. S.-J. Yun and Y-H. Oh, 'Performance improvement of speaker recognition system for small training data,' in Proceedings of ICSLP, Yokohama, pp.1863-1866, 1994
  12. X. D. Huang, Y. Ariki, and M. A. Jack, 'Hidden Markov models for speech recognition,' Redwood Press Limited, 1990
  13. J. Godfrey, D. Graff, and A. Martin, 'Public databases for speaker recognition and verification,' ESCA Workshop on Automatic Speaker Recognition Identification and Verification, pp.39-42, 1994
  14. C.-C. T. Chen, C.-T. Chen, and C.-M. Tsai, 'Hard-limited Karhunen-Loeve transform for text independent speaker recognition,' Electronics Letters, vol.33, pp.2014-2016, 1997 https://doi.org/10.1049/el:19971429
  15. J.-H. Kim, G.-J. Jang, S.-J. Yun, and Y.-H. Oh, 'Candidate selection based on significance testing and its use in normalisation and scoring,' in Proceedings of ICSLP, pp.141-144, 1998