Post-processing for Enhancing Target Signal in Frequency Domain Blind Source Separation

  • Hyuntae Kim
  • Jangsik Park
  • Keunsoo Park
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


The performance of blind source separation (BSS) using independent component analysis (ICA) declines significantly in a reverberant environment. The degradation is mainly caused by the residual crosstalk components derived from the reverberation of the interference signal. A post-processing method is proposed in this paper which uses a approximated Wiener filter using short-time magnitude spectra in the spectral domain. The speech signals have a sparse characteristic in the spectral domain, hence the approximated Wiener filtering can be applied by endowing the difference weights to the other signal components. The results of the experiments show that the proposed method improves the noise reduction ratio(NRR) by about 3dB over conventional FDICA. In addition, the proposed method is compared to the other post-processing algorithm using NLMS algorithm for post-processor [6], and show the better performances of the proposed method.


Independent Component Analysis Speech Signal Independent Component Analysis Spectral Domain 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. 1.
    Hyvarinen, A., Karhnen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, Chichester (2001)CrossRefGoogle Scholar
  2. 2.
    Makeig, S., Jung, T., Bell, A.J., Ggahremani, D., Seijnowski, T.J.: Blind separation of auditory event-related brain response into independent components. In: Proceedings on National Academic Science, USA, pp. 10979–10984 (1997)Google Scholar
  3. 3.
    Araki, S., Makino, S., Nishikawa, T., Saruwatari, H.: Fundamental limitation of frequency domain blind separation for convolutive mixture of speech. In: Proc. ICASSP 2001, pp. 2737–2740 (2001)Google Scholar
  4. 4.
    Ikram, M.Z., Morgan, D.R.: Exploring permutaion inconsistency in blind separation of speech signals in a reverberant environment. In: Proc. of ICASSP 2000, pp. 1041–1044 (2000)Google Scholar
  5. 5.
    Mukai, R., Araki, S., Makino, S.: Separation and dereverbration performance of frequency domain blind source separation. In: Proc. of Int. Conf. on Independent Component Analysis and Blind Signal Separation (ICA 2001), pp. 230–235 (2001)Google Scholar
  6. 6.
    Mukai, R., Araki, S., Sawada, H., Makino, S.: Removal of residual crosstalk components in blind source separation using LMS filters. In: Proc. ICASSP 2002, pp. 435–444 (2002)Google Scholar
  7. 7.
    Low, S.Y., Nordholm, S., Togneri, R.: Convolutive blind signal separation with post-processing. IEEE Trans. on speech and audio processing 12(5) (2004)Google Scholar
  8. 8.
    Araki, S., Blin, A., Mukai, R., Sawada, H., Makino, S.: Underdetermined blind separation for speech in real environments with sparseness and ICA. In: Proc. ICASSP 2004, vol. 3(17-21), pp. 881–884 (2004)Google Scholar
  9. 9.
    Amari, S.I., Cichocki, A., Yang, H.H.: A new learning algorithm for blind signal separation. In: Advances in Neural Information Processing Systems, vol. 8. MIT Press, Cambridge (1996)Google Scholar
  10. 10.
    Murata, N., Ikeda, S., Ziehe, A.: An approach to blind source separation based on temporal structure of speech signals. Neurocomputing 41, 1–24 (2001)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hyuntae Kim
    • 1
  • Jangsik Park
    • 2
  • Keunsoo Park
    • 3
  1. 1.Department of Multimedia EngineeringDongeui UniversityBusanKorea
  2. 2.Department of Digital Inform. Electronic EngineeringDongeui Institute of TechBusanKorea
  3. 3.Department of Electronic EngineeringPusan National UniversityBusanKorea

Personalised recommendations