The Journal of the Acoustical Society of Korea

The Acoustical Society of Korea (한국음향학회)
권호 표지

Statistical Extraction of Speech Features Using Independent Component Analysis and Its Application to Speaker Identification

  • Jang, Gil-Jin (Department of Computer Science, Korea Advanced Institute of Science and Technology) ;
  • Oh, Yung-Hwan (Department of Computer Science, Korea Advanced Institute of Science and Technology)
  • Published : 2002.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

We apply independent component analysis (ICA) for extracting an optimal basis to the problem of finding efficient features for representing speech signals of a given speaker The speech segments are assumed to be generated by a linear combination of the basis functions, thus the distribution of speech segments of a speaker is modeled by adapting the basis functions so that each source component is statistically independent. The learned basis functions are oriented and localized in both space and frequency, bearing a resemblance to Gabor wavelets. These features are speaker dependent characteristics and to assess their efficiency we performed speaker identification experiments and compared our results with the conventional Fourier-basis. Our results show that the proposed method is more efficient than the conventional Fourier-based features in that they can obtain a higher speaker identification rate.

Keywords

References

  1. R. J. Mammone, X. Zhang, and R. P. Ramachandran, 'Robust speaker recognition: a feature-based approach,' IEEE signal processing magazaine, 58-71, 9, 1996
  2. P. Comon, 'Independent component analysis, A new concept?,' Signal Processing, 36, 287-314, 1994 https://doi.org/10.1016/0165-1684(94)90029-9
  3. A. J. Bell and T. J. Sejnowski, 'An information-maximization approach to blind separation and blind deconvolution,' Neural Computation, 7 (6), 1004-1034, 1995
  4. G.-J. Jang, S.-J. Yun, and Yung-Hwan, 'Feature vector transformation using independent component analysis and its application to speaker identification,' In Proceedings of Eurospeech, (Budapest Hungary), 767-760, Sept 1999
  5. H. Hermansky, S. Sharma, and P. Jain, 'Data-drived non-linear mapping for feature extraction in HMM,' In Proceeding of the Workshop on Automatic Speech Recognition and Understanding, (Keystone, CO., USA), December 1999
  6. J.-H. Lee, H.-Y. Jung, T.-W. Lee, and S.-Y. Lee, 'Speech feature extraction using independent component analysis,' In Proc. ICASSP, 3, (Istanbul, Turkey), 1631-1634, Jun 2000
  7. B. A. Olshausen and D. J. Field, 'Emergence of simple-cell receptive-field properties by learning a sparse code for natural images,' Nature, 381, 607-609, 1996 https://doi.org/10.1038/381607a0
  8. A. Hyvaerinen, 'Sparse code shrinkage: denoising of non-gaussian data by maximum likelihood estimation,' Neural Computation, 11 (7), 1739-1768, 1999 https://doi.org/10.1162/089976699300016214
  9. T.-W. Lee and M. S. Lewicki, 'The generalized Gaussian mixture model using ICA,' In International Workshop on Independent Component Analysis (ICA'00), (Helsinki), 239-244, Jun 2000
  10. C. Jutten and J. Herault, 'Blind separation of sources, Part I: An adaptive algorithm based on neuromimetic architecture,' Signal Processing, 24, 1-10, 1991 https://doi.org/10.1016/0165-1684(91)90079-X
  11. D. T. Pham and P. Garrat, 'Blind source separation of mixture of independent sources through a quasi-maximum likelihood approach,' IEEE Trans. on Signal Proc., 45 (7), 1712-1725, 1997 https://doi.org/10.1109/78.599941
  12. T.-W. Lee and G.-J. Jang, 'The statistical structures of male and female speech signals,' In Proc. ICASSP, (Salt Lake City, Utah), May 2001