Skip to main content
SpringerLink
Log in

Single-Channel Source Separation of Audio Signals Using Bark Scale Wavelet Packet Decomposition

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

We address the problem of blind source separation from a single channel audio source using a statistical model of the sources. We modify the Bark Scale aligned Wavelet Packet Decomposition, to acquire approximate-shiftability property. We allow oversampling in some decomposition nodes to equalize sampling rate in all terminal nodes. Statistical models are trained from samples of each source separately. The separation is performed using these models. The proposed psycho-acoustically motivated non-uniform filterbank structure reduces signal space dimension and simplifies training procedure of the statistical model. In our experiments we show that the proposed algorithm performs better when compared to a competing algorithm. We study the effect that different wavelet families have on the performance of the proposed signal analysis in the single-channel source separation task.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11

Similar content being viewed by others

References

  1. Vincent, E., Févotte, C., Benaroya, L., & Gribonval, R. (2003). A tentative typology of audio source separation tasks. In Proc. 4th international symposium on independent component analysis and blind signal separation (ICA2003) (pp. 715–720). Nara, Japan.

    Google Scholar 

  2. Cherry, C. E. (1953). Some experiments on the recognition of speech, with one and with two ears. Journal of the Acoustical Society of America, 25(5), 975–979.

    Article  Google Scholar 

  3. Comon P. (1994). Independent component analysis, a new concept? Signal Processing, 36(3), 287–314.

    Article  MATH  Google Scholar 

  4. Hyvärinen, A., Karhunen, J., & Oja, E. (2001). Independent component analysis. Wiley-Interscience.

  5. Ozerov, A., Philippe, P., Bimbot, F., & Gribonval, R. (2007). Adaptation of bayesian models for single-channel source separation and its application to voice/music separation in popular songs. IEEE Transactions on Audio, Speech & Language Processing, 15(5), 1564–1578.

    Article  Google Scholar 

  6. Benaroya, L., Bimbot, F., & Gribonval, R. (2006). Audio source separation with a single sensor. IEEE Transactions on Audio, Speech & Language Processing, 14(1), 191–199.

    Article  Google Scholar 

  7. Benaroya, L., & Bimbot, F. (2003). Wiener based source separation with HMM/GMM using a single sensor. In Proc. 4th international symposium on independent component analysis and blind signal separation (ICA2003) (pp. 957–961). Nara, Japan.

    Google Scholar 

  8. Srinivasan, S., Samuelsson, J., & Kleijn, W. B. (2006). Codebook driven short-term predictor parameter estimation for speech enhancement. IEEE Transactions on Audio, Speech & Language Processing, 14(1), 163–176.

    Article  Google Scholar 

  9. Srinivasan, S., Samuelsson, J., & Kleijn, W. B. (2007). Codebook-based bayesian speech enhancement for nonstationary environments. IEEE Transactions on Audio, Speech & Language Processing, 15(2), 441–452.

    Article  Google Scholar 

  10. Cohen, I. (2001). Enhancement of speech using bark-scaled wavelet packet decomposition. In Proc. 7th European conf. speech, communication and technology, EUROSPEECH-2001 (pp. 1933–1936). Aalborg, Denmark.

    Google Scholar 

  11. Fernandes, F. C .A., van Spaendonck, R. L. C., & Burrus, C. S. (2003). A new framework for complex wavelet transforms. IEEE Transactions Signal Processing, 51(7), 1825–1837.

    Article  Google Scholar 

  12. Litvin, Y., & Cohen, I. (2009). Single-channel source separation of audio signals using bark scale wavelet packet decomposition. In 2009 IEEE international workshop on machine learning for signal processing (MLSP09).

  13. Fernandes, F. C. A. (2002). Directional, shift-insensitive, complex wavelet transforms with controllable redundancy. Ph.D. thesis, Rice Univ., Houston, TX, USA.

  14. Simoncelli, E. P., Freeman, W. T., Adelson, E. H., & Heeger, D. J. (1992). Shiftable multiscale transforms. IEEE Transactions on Information Theory, 38(2), 587–607.

    Article  MathSciNet  Google Scholar 

  15. Ephraim, Y., & Malah, D. (1984). Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Transactions on Acoustics, Speech, and Signal Processing, 32(6), 1109–1121.

    Article  Google Scholar 

  16. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 39(1), 1–38.

    MathSciNet  MATH  Google Scholar 

  17. Gribonval, R., Benaroya, L., Vincent, E., & Févotte, C. (2003). Proposals for performance measurement in source separation. In Proc. 4th international symposium on ICA and BSS (ICA2003) (pp. 763–768). Nara, Japan.

    Google Scholar 

  18. Févotte, C., Gribonval, R., & Vincent, E. (2005). BSS_EVAL toolbox user guide revision 2.0. Tech. Rep. 1706, IRISA, Rennes, France.

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Technion—Israel Institute of Technology, Technion City, Haifa, 32000, Israel

    Yevgeni Litvin & Israel Cohen

Authors
  1. Yevgeni Litvin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Israel Cohen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yevgeni Litvin.

Additional information

This work was supported by the Israel Science Foundation under Grant 1085/05 and by the European Commission under project Memories FP6-IST-035300.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Litvin, Y., Cohen, I. Single-Channel Source Separation of Audio Signals Using Bark Scale Wavelet Packet Decomposition. J Sign Process Syst 65, 339–350 (2011). https://doi.org/10.1007/s11265-010-0510-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-010-0510-9

Keywords

Search

Navigation