access icon free Blind signal separation method and relationship between source separation and source localisation in the TF plane

A method for solving the instantaneous mixtures of the multiple non-stationary wideband signals in the time–frequency (TF) plane is proposed. The blind source separation is performed by calculation of spatial TF distribution matrices, estimation of a separating matrix, estimation of permutation matrices and scaling matrices and TF synthesis. The simulation result shows that the proposed method improves the signal-to-distortion ratio than the preceding methods. Moreover, also the mutual relationship between the source localisation and the source separation is clarified. The source localisation methods using the source separation result and the source separation method using the source localisation result are proposed.

Inspec keywords: estimation theory; blind source separation; matrix algebra

Other keywords: signal-to-distortion ratio; permutation matrices estimation; TF plane; TF synthesis; multiple nonstationary wideband signals; time-frequency plane; source separation method; separating matrix estimation; scaling matrices estimation; spatial TF distribution matrices; source localisation methods; instantaneous mixtures; blind signal separation method

Subjects: Algebra; Algebra; Other topics in statistics; Signal processing and detection; Other topics in statistics; Signal processing theory

References

    1. 1)
      • 1. Benesty, J., Chen, J., Huang, Y.: ‘Microphone array signal processing’ (Springer-Verlag, Berlin Heidelberg, 2008), p. 240, ISBN 978-3-540-78611-5.
    2. 2)
      • 2. Huang, Y., Benesty, J., Chen, J.: ‘Acoustic MIMO signal processing’ (Springer-Verlag, Berlin Heidelberg, Germany, 2006), p. 378, ISBN 10 3-540-37630-5.
    3. 3)
      • 22. Comon, P.: ‘Independent component analysis, a new concept’, Signal Process., 1994, 36, (3), pp. 287314.
    4. 4)
      • 17. Lu, F., Huang, Z., Jiang, W.: ‘Underdetermined blind separation of non-disjoint signals in time–frequency domain based on matrix diagonalization’, Signal Process., 2011, 91, pp. 15681577.
    5. 5)
      • 20. Thomas, J., Deville, Y., Hosseini, S.: ‘Time-domain fast fixed-point algorithms for instantaneous ICA’, IEEE Signal Process. Lett., 2006, 13, (4), pp. 228231.
    6. 6)
      • 16. Chabriel, G., Barrère, J., Moreau, N.T., et al: ‘Algebraic joint zero-diagonalization and blind sources separation’, IEEE Trans. Signal Process., 2008, 56, (3), pp. 980989.
    7. 7)
      • 35. Vincent, E., Gribonval, R., Févotte, C.: ‘Performance measurement in blind audio source separation’, IEEE Trans. Audio Speech Lang. Process., 2006, 14, (4), pp. 14621469.
    8. 8)
      • 12. Hyvarinen, A., Oja, E.: ‘A fast fixed-point algorithm for independent component analysis’, Neural Comput., 1997, 9, pp. 14831492.
    9. 9)
      • 4. Belouchrani, A., Meraim, K.A., Cardoso, J.F., et al: ‘A blind source separation technique using second-order statistics’, IEEE Trans. Signal Process., 1997, 45, (2), pp. 434444.
    10. 10)
      • 34. Wax, M., Sheinvald, J.: ‘A least-squares approach to joint diagonalization’, IEEE Signal Process. Lett., 1997, 4, pp. 5253.
    11. 11)
      • 26. Sawada, H., Mukai, R., Araki, S., et al: ‘A robust and precise method for solving the permutation problem of instantaneous-domain blind source separation’, IEEE Trans. Speech Audio Process., 2004, 12, (5), pp. 530538.
    12. 12)
      • 6. Curnew, S.R.: ‘Independent component analysis for blind source separation in MIMO-OFDM system’ (Dalhouse University, Halifax, Nova Scotia, 2007), p. 66.
    13. 13)
      • 24. Liu, Q., Wang, W., Jackson, P.: ‘Use of bimodal coherence to resolve the permutation problem in instantaneous BSS’, Signal Process., 2012, 92, pp. 19161927.
    14. 14)
      • 13. Pham, D.-T.: ‘Joint approximate diagonalization of positive definite matrices’, SIAM J. Matrix Anal. Appl., 2001, 22, (4), pp. 11361152.
    15. 15)
      • 27. Yilmaz, Ö, Rickard, S.: ‘Blind separation of speech mixtures via time–frequency masking’, IEEE Trans. Signal Process., 2004, 52, (7), pp. 18301847.
    16. 16)
      • 30. Boashash, B.: ‘Time instantaneous signal analysis and processing’ (SPRQ University of Technology Brisbane, Australia, 2003), p. 743, ISBN 0-08-044335-4.
    17. 17)
      • 21. Mei, T., Xi, J., Yin, F., et al: ‘Blind source separation based on time-domain optimization of an instantaneous-domain independence criterion’, IEEE Trans. Audio Speech Lang. Process., 2006, 14, (6), pp. 20752085.
    18. 18)
      • 15. Yeredor, A., Ziehe, A., Müller, K.-R.: ‘Approximate joint diagonalization using natural gradient approach’. Proc. ICA: Independent Component Analysis and Blind Sources Separation, Granada, Spain, September 2004, (LNCS, 3195), pp. 8996.
    19. 19)
      • 28. Tengtrairat, N., Gao, B., Woo, W.L., et al: ‘Online noisy single-channel source separation by adaptive spectrum amplitude estimator and masking’, IEEE Trans. Signal Process., 2016, 64, (7), pp. 18811895.
    20. 20)
      • 18. Bourgeois, J., Minker, W.: ‘Time-domain beamforming and blind source separation’ (Springer Dordrecht, Springer Science+Business Media, LLC, Heidelberg, London, New York, 2007), p. 225, ISBN 978-0-387-68835-0.
    21. 21)
      • 7. Herault, J., Jutten, C., Ans, B.: ‘Detection de grandeurs primitives dans un message composite par une architecture de calul neuromimetique un apprentissage non supervise’. Proc. Groupe d'Etudes du Traitement du Signal et des Images, France, 1985.
    22. 22)
      • 9. Moreau, E., Macchi, O.: ‘New self-adaptive algorithms for source separation based on contrast functions’. Proc. IEEE Signal Processing Workshop, Higher Order Statistics, Lake Tahoe, CA, 1993.
    23. 23)
      • 3. Belouchrani, A., Amin, M.G.: ‘Blind source separation based on time–instantaneous signal representations’, IEEE Trans. Signal Process., 1998, 46, (11), pp. 28882897.
    24. 24)
      • 19. Amari, S., Douglas, S.C., Cichocki, A., et al: ‘Multichannel blind deconvolution and equalization using the natural gradient’. Proc. IEEE Int. Workshop on Wireless Communication, France, 1997, pp. 101104.
    25. 25)
      • 14. Ziehe, A., Laskov, P., Nolte, G., et al: ‘A fast algorithm for joint diagonalization with non-orthogonal transformations and its application to blind source separation’, J. Mach. Learn. Res., 2004, 5, pp. 777800.
    26. 26)
      • 36. Cholnam, O., Dokkil, K., Cholyong, J.: ‘Spatial spectrum for direction of arrival estimation of multiple non-stationary wideband sources in the time–frequency plane’, IET Signal Process., 2016, 10, (9), pp. 11051111.
    27. 27)
      • 33. Sharif, W., Chakhchoukh, Y., Zoubir, A.M.: ‘Robust spatial time–frequency distribution matrix estimation with application to direction-of-arrival estimation’, Signal Process., 2011, 91, pp. 26302638.
    28. 28)
      • 25. Asano, F., Ikeda, S., Ogawa, M., et al: ‘Combined approach of array processing and independent component analysis for blind separation of acoustic signals’, IEEE Trans. Speech Audio Process., 2003, 11, (3), pp. 204215.
    29. 29)
      • 10. Belouchrani, A., Cardoso, J.-F.: ‘Maximum likelihood source separation for discrete sources’. Proc. European Signal Processing Conf., Edinburgh, Scotland, 1994, pp. 768771.
    30. 30)
      • 5. Cichocki, A., Amari, S.: ‘Adaptive blind signal and image processing’ (John Wiley & Sons Ltd., Springer Dordrecht Heidelberg London New York, 2002), p. 555, ISBN 0471 60791 6.
    31. 31)
      • 11. Bell, A.J., Sejnowski, T.J.: ‘An information-maximization approach to blind separation and blind convolution’, Neural Comput., 1995, 7, (6), pp. 11291159.
    32. 32)
      • 23. Ikhlef, A., Meraim, K.A., Guennec, D.L.: ‘Blind source separation and equalization with controlled delay for MIMO instantaneous systems’, Signal Process., 2010, 90, pp. 26552666.
    33. 33)
      • 8. Cardoso, J.-F., Souloumiac, A.: ‘Blind beamforming for non-Gaussian signals’, IEE Proc. F, Radar Signal Process., 1993, 140, (6), pp. 362370.
    34. 34)
      • 29. Tengtrairat, N., Parathai, P., Woo, W.L.: ‘Blind 2D signal direction for limited-sensor space using maximum likelihood estimation’, Asia Pac. J. Sci. Technol., 2017, 22, (2), pp. 4249.
    35. 35)
      • 31. Cirillo, L., Zoubir, A., Amin, M.: ‘Blind source separation in the time–frequency domain based on multiple hypothesis testing’, IEEE Trans. Signal Process., 2008, 56, (6), pp. 22672279.
    36. 36)
      • 32. Visse, E.: ‘Frequency domain passive broadband speaker localization using a permutation-free blind source separation algorithm’. IEEE Int. Conf. Acoustics, Speech and Signal Processing – (ICASSP'07), Honolulu, HI, USA, 2007, pp. 673678.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2018.5132
Loading

Related content

content/journals/10.1049/iet-spr.2018.5132
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading