Blind Source Separation Using Graphical Models

  • Te-Won Lee


We summarized our approaches for separating voices from mixed recordings. In the single channel case, a priori learned basis functions are used to model the temporal structure of the speech signals. A maximum likelihood approach is used to separate a voice from jazz music given only one mixed channel. In case of two microphones, the problem of separating two voices recorded by two microphones has been tackled. The mixing coefficients, time delays and reverberation coefficients are estimated using the maximum likelihood or infomax approach. The two approaches can be combined in a graphical model since both methods can be represented as data generative models where learning involves the representation of signals via the basis functions and inference involves the estimation of sources. The inference part in case of the single channel is nonlinear and linear in the two channel case.


Independent Component Analysis Speech Signal Independent Component Analysis Source Separation Blind Source Separation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Acero, A., 1990, Acoustical and Environmental Robustness for Automatic Speech Recognition, Ph.D. Thesis, ECE Department, CMU, September 1990.Google Scholar
  2. Attias, H., 1999, Independent factor analysis. Neural Computation, 11(4):803–852.CrossRefGoogle Scholar
  3. Attias, H., 2003, Source separation with a sensor array using graphical models and subband filtering. Advances in Neural Information Processing Systems 15, MIT Press, CambridgeGoogle Scholar
  4. Bell, A.J., and Sejnowski, T.J., 1995, An information-maximization approach to blind separation and blind deconvolution, Neural Computation 7:1129–1159.Google Scholar
  5. Bell, A.J., and Sejnowski, T.J., 1996, Learning the higher-order structure of a natural sound. Network: Computation in Neural Systems, 7:261–266.CrossRefGoogle Scholar
  6. Bregman, A.S. 1990, Auditory scene analysis: The perceptual organization of sound, MIT PressGoogle Scholar
  7. Brown, G.J., and Cooke, M., 1994, Computational auditory scene analysis. Computer speech and language, 8:297–336.Google Scholar
  8. de Cheveigné A., 2001, The auditory system as a separation machine, in Physiological and Psychophysical Bases of Auditory Function, J. Breebaart, A.J.M. Houtsma, A. Kohlrausch, V.F. Prijs and R. Schoonhoven, eds., Shaker Publishing BV, Maastricht, The Netherlands, pp. 453–460.Google Scholar
  9. Chan, K.-L., Lee, T.-W. and Sejnowski, T.S., 2002, Variational Learning of Clusters of Under-complete Nonsymmetric Independent Components, Journal of Machine Learning Research, Vol 3, 99–114.MathSciNetGoogle Scholar
  10. Comon, P., 1994, Independent component analysis, A new concept? Signal Processing, 36:287–314.CrossRefzbMATHGoogle Scholar
  11. Cooke, M., Ellis, D., 2001, The auditory organization of speech and other sources in listeners and computational models, Speech Communication 35, 141–177.CrossRefGoogle Scholar
  12. Darwin, C., Carlyon, R., 1995, Auditory grouping, in The book of perception and Cognition, Vol 6, Hearing, B.C.J. Moore, ed., Academic Press, New York, pp. 387–424.Google Scholar
  13. Ellis, D.P.W., 1994, A computer implementation of psychoacoustic grouping rules. Proceedings of the 12th International Conference on Pattern Recognition, 1994.Google Scholar
  14. Haykin, S., editor, 1994, Blind Deconvolution. Prentice Hall, Englewood Cliffs, New Jersey.Google Scholar
  15. Huang, X., Acero, A., and Hon, H.-W., 2001, Spoken Language Processing. Prentice Hall, Englewood Cliffs, New Jersey.Google Scholar
  16. Hyvärinen, A., Karhunen, J. and Oja, E., 2002, Independent Component Analysis, John Wiley and Sons.Google Scholar
  17. Jang, G.-J., and Lee, T.-W., 2003, A probabilistic approach to single channel source separation. Advances in Neural Information Processing Systems 15, MIT Press, Cambridge.Google Scholar
  18. Jordan, M.I., Ghahramani, Z., and Jaakkola, T.S., 1998, An introduction to variational methods for graphical models, in Learning in Graphical Models, M. I. Jordan, ed., MIT Press, Cambridge, pp. 105–161.Google Scholar
  19. Lambert, R, Multichannel blind deconvolution: Fir matrix algebra and separation of multipath mixtures. Thesis, University of Southern California, Department of Electrical Engineering.Google Scholar
  20. Lee, T., Bell, A., and Lambert, R., 1997, Blind separation of convolved and delayed sources, in Advances in Neural Information Processing Systems 9. MIT Press, Cambridge.Google Scholar
  21. Lee, T.-W., 1998, Independent Component Analysis: Theory and Applications, Kluwer Academic Publishers, Boston.Google Scholar
  22. Roweis, S.T., 2001, One microphone source separation. Advances in Neural Information Processing Systems 13.Google Scholar
  23. Stern, R.M., Acero, A., Liu, F.-H., and Ohshima, Y., 1996, Signal Processing for Robust Speech Recognition, in Speech Recognition, C.-H. Lee and F. Soong, eds., Kluwer Academic Publishers, Boston, pp. 351–378.Google Scholar
  24. Torkkola, K., 1996, Blind separation of convolved sources based on information maximization. IEEE Workshop on Neural Networks for Signal Processing, Kyoto, Japan, September 4–6.Google Scholar
  25. Visser, E., Otsuka, M., Lee, T.-W., 2003, A Spatio-Temporal Speech Enhancement Scheme for Robust Speech Recognition in Noisy Environments, Speech Communications, Vol 41, Issues 2–3, Pages 393–407.Google Scholar
  26. Wang, D., Brown, G., 1999, Separation of speech from interfering sounds based on oscillatory correlation. IEEE Transactions on Neural Networks 10(3), 684–697.MathSciNetGoogle Scholar
  27. Yellin, D. and Weinstein, E., 1996, Multichannel signal separation: Methods and analysis. IEEE Transactions on Signal Processing, 44(1): 106–118.CrossRefGoogle Scholar

Copyright information

© Springer Science + Business Media, Inc. 2005

Authors and Affiliations

  • Te-Won Lee
    • 1
  1. 1.Institute for Neural ComputationUniversity of CaliforniaSan Diego

Personalised recommendations