Estimator for Number of Sources Using Minimum Description Length Criterion for Blind Sparse Source Mixtures

  • Radu Balan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4666)

Abstract

In this paper I present a Minimum Description Length Estimator for number of sources in an anechoic mixture of sparse signals. The criterion is roughly equal to the sum of negative normalized maximum log-likelihood and the logarithm of number of sources. Numerical evidence supports this approach and compares favorabily to both the Akaike (AIC) and Bayesian (BIC) Information Criteria.

Keywords

Maximum Likelihood Estimator Blind Source Separation Minimum Description Length Sparse Signal Uniform Linear Array 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yilmaz, O., Rickard, S.: Blind separation of speech mixtures via time-frequency masking. IEEE Trans. on Sig. Proc. 52(7), 1830–1847 (2004)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Rickard, S., Balan, R., Rosca, J.: Real-time time-frequency based blind source separation. In: Proc. ICA, pp. 651–656 (2001)Google Scholar
  3. 3.
    Balan, R., Rosca, J., Rickard, S.: Non-square blind source separation under coherent noise by beamforming and time-frequency masking. In: Proc. ICA (2003)Google Scholar
  4. 4.
    Balan, R., Rosca, J., Rickard, S.: Scalable non-square blind source separation in the presence of noise. In: ICASSP 2003, Hong-Kong, China (April 2003)Google Scholar
  5. 5.
    Rosca, J., Borss, C., Balan, R.: Generalized sparse signal mixing model and application to noisy blind source separation. In: Proc. ICASSP (2004)Google Scholar
  6. 6.
    Balan, R., Rosca, J.: Convolutive demixing with sparse discrete prior models for markov sources. In: Proc. BSS-ICA (2006)Google Scholar
  7. 7.
    Balan, R., Rosca, J.: Map source separation using belief propagation networks. In: Proc. ASILOMAR (2006)Google Scholar
  8. 8.
    Aoki, M., Okamoto, M., Aoki, S., Matsui, H.: Sound source segregation based on estimating incident angle of each frequency component of input signals acquired by multiple microphones. Acoust. Sci. & Tech. 22(2), 149–157 (2001)CrossRefGoogle Scholar
  9. 9.
    Sawada, H., Mukai, R., Araki, S., Makino, S.: A robust and precise method for solving the permutation problem of frequency-domain blind source separation. IEEE Trans. SAP 12(5), 530–538 (2004)Google Scholar
  10. 10.
    Georgiev, P., Theis, F., Cichocki, A.: Sparse component analysis and blind source separation of underdetermined mixtures. IEEE Tran. Neur.Net. 16(4), 992–996 (2005)CrossRefGoogle Scholar
  11. 11.
    Cichocki, A., Li, Y., Georgiev, P., Amari, S.-I.: Beyond ica: Robust sparse signal representations. In: IEEE ISCAS Proc. pp. 684–687 (2004)Google Scholar
  12. 12.
    Cichocki, A., Amari, S.: Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. Wiley, Chichester (April 2002)Google Scholar
  13. 13.
    Comon, P.: Independent component analysis, a new concept? Signal Processing 36(3), 287–314 (1994)MATHCrossRefGoogle Scholar
  14. 14.
    Bell, A.J., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Computation 7, 1129–1159 (1995)CrossRefGoogle Scholar
  15. 15.
    Annemuller, J., Kollmeier, B.: Amplitude modulation decorrelation for convolutive blind source separation. In: ICA, pp. 215–220 (2000)Google Scholar
  16. 16.
    Bofill, P., Zibulevsky, M.: Blind separation of more sources than mixtures using sparsity of their short-time Fourier transform. In: Proc. ICA, Helsinki, Finland, pp. 87–92 (June 19-22, 2000)Google Scholar
  17. 17.
    Akaike, H.: A new look at the statistical model identification. IEEE Trans. Aut. Cont. 19(6), 716–723 (1974)MATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Barron, A., Rissanen, J., Yu, B.: The minimum description length principle in coding and modeling. IEEE Trans. Inf. Th. 44(6), 2743–2760 (1998)MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Schwarz, G.: Estimating the dimension of a model. Ann. Statist. 6(2), 461–464 (1978)MATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Rissanen, J.: Modeling by shortest data description. Automatica 14, 465–471 (1978)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Radu Balan
    • 1
  1. 1.Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540 

Personalised recommendations