Householder transform based joint diagonal zero diagonalization for source separation using time-frequency distributions

Article
First Online:
Received:
Revised:
Accepted:

Abstract

We present a new combined joint diagonalization and zero diagonalization algorithm for separating the source signals by using time-frequency distributions (TFD). The proposed algorithm is based on the Householder transform, which exactly guarantees the orthonormality of the diagonalizer and/or zero diagonalizer. As an application, we show that blind separation of correlated sources can be achieved by applying the proposed algorithm to spatial quadratic TFD matrices corresponding to auto-source terms and/or cross-source terms. Computer simulations are provided to demonstrate the performances of the proposed algorithm and compare it with the classical ones to show the performance improvement.

Keywords

Joint diagonalization Joint zero diagonalization Blind source separation (BSS) Quadratic time-frequency distributions 
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. Belouchrani A., Amin M. G. (1998) Blind source separation based on time-frequency signal representations. IEEE Transactions on Signal Processing 46(11): 2888–2897CrossRefGoogle Scholar
  2. Belouchrani A., Abed-Meraim K., Cardoso J.-F. (1997) A blind source separation technique using second order statistics. IEEE Transactions on Signal Processing 45(2): 434–444CrossRefGoogle Scholar
  3. Belouchrani A., Abed-Meraim K., Amin M. G. et al (2004) Blind separation of nonstationary sources. IEEE Signal Processing Letters 11(7): 605–608CrossRefGoogle Scholar
  4. Brewer J. W. (1978) Kronecker products and matrix calculus in system theory. IEEE Transactions on circuits and systems 25(9): 772–781MATHCrossRefMathSciNetGoogle Scholar
  5. Cardoso J.-F., Souloumiac A. (1993) Blind beamforming for non Gaussian signals. IEEE Proceedings Part F: Radar and Signal Processing 140(6): 362–370Google Scholar
  6. Cardoso J.-F., Souloumiac A. (1996) Jacobi angles for simultaneous diagonalization. SIAM Journal on Matrix Analysis and Applications 17(1): 161–164MATHCrossRefMathSciNetGoogle Scholar
  7. Chabriel G., Barrere J., Thirion-Moreau N. et al (2008) Algebraic joint zero-diagonalization and blind sources separation. IEEE Transactions on Signal Processing 56(3): 980–989CrossRefMathSciNetGoogle Scholar
  8. Cohen L. (1995) Time-frequency analysis. Prentice-Hall, Englewood Cliffs, NJGoogle Scholar
  9. Degerine S., Kane E. (2007) A comparative study of approximate joint diagonalization algorithms for blind source separation in presence of additive noise. IEEE Transactions on Signal Processing 55(6): 3022–3031CrossRefMathSciNetGoogle Scholar
  10. Fadaili E. M., Thirion-Moreau N., Moreau E. (2007) Nonorthogonal joint diagonalization/zero diagonalization for source separation based on time-frequency distributions. IEEE Transactions on Signal Processing 55(5): 1673–1687CrossRefMathSciNetGoogle Scholar
  11. Fevotte C., Doncarli C. (2004) Two contributions to blind source separation using time-frequency distributions. IEEE Signal Processing Letters 11(3): 386–389CrossRefGoogle Scholar
  12. Giulieri L., Ghennioui H., Thirion-Moreau N. et al (2005) Nonorthogonal joint diagonalization of spatial quadratic time-frequency matrices for source separation. IEEE Signal Processing Letters 12(5): 415–418CrossRefGoogle Scholar
  13. Golub G. H., Van Loan C.-F. (1996) Matrix computations (3rd ed.). The Johns Hopkins University Press, Baltimore, MDMATHGoogle Scholar
  14. Li X.-L., Zhang X.-D. (2007) Nonorthogonal joint diagonalization free of degenerate solution. IEEE Transactions on Signal Processing 55(5): 1803–1814CrossRefMathSciNetGoogle Scholar
  15. Tichavsky P., Yeredor A. (2009) Fast approximate joint diagonalization incorporating weight matrices. IEEE Transactions on Signal Processing 57(3): 878–891CrossRefGoogle Scholar
  16. Vollgraf R., Obermayer K. (2006) Quadratic optimization for simultaneous matrix diagonalization. IEEE Transactions on Signal Processing 54(9): 3270–3278CrossRefGoogle Scholar
  17. Yeredor A. (2002) Non-orthogonal joint diagonalization in the least square sense with application in blind source separation. IEEE Transactions on Signal Processing 50(7): 1545–1553CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.School of Electronic EngineeringXidian UniversityXi’anChina

Personalised recommendations