Phonetics and Speech Sciences (말소리와 음성과학)

Korean Society of Speech Sciences (한국음성학회)
권호 표지
DOI QR코드

DOI QR Code

Frequency Bin Alignment Using Covariance of Power Ratio of Separated Signals in Multi-channel FD-ICA

다채널 주파수영역 독립성분분석에서 분리된 신호 전력비의 공분산을 이용한 주파수 빈 정렬

  • Received : 2014.05.19
  • Accepted : 2014.09.11
  • Published : 2014.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In frequency domain ICA, the frequency bin permutation problem falls off the quality of separated signals. In this paper, we propose a new algorithm to solve the frequency bin permutation problem using the covariance of power ratio of separated signals in multi-channel FD-ICA. It makes use of the continuity of the spectrum of speech signals to check if frequency bin permutation occurs in the separated signal using the power ratio of adjacent frequency bins. Experimental results have shown that the proposed method could fix the frequency bin permutation problem in the multi-channel FD-ICA.

Keywords

References

  1. Haykin, S. (2009). Neural networks and learning machines, USA: Pearson Prentice Hall.
  2. Cichocki, A and Amari, S. (2002). Adaptive blind signal and image processing (learning algorithms and applications), New York: John Wiley & Sons.
  3. Matsuoka, K (2002). Minimal distortion principle for blind source separation, Proceedings of the 41st SICE Annual Conference. Vol. 4, pp. 2138-2143.
  4. Lee, T. W. & Bell, A. J. & Lambert, R. H. (1997). Blind separation of delayed and convolved sources, Advances in neural information processing systems, pp. 758-764.
  5. Sawada, H. & Mukai, R. & Araki, S. & Makino, S. (2001). A polar-coordinate based activation function for frequency domain blind source separation, Int. Conf. ICA and BSS, pp. 663-668.
  6. Sawada, H. & Araki, S. & R. Mukai, R. & Makino, S. (2007). Grouping separated frequency components by estimating propagation model parameters in frequency-domain blind source separation, Audio, Speech, and Language Processing, IEEE Transactions on. Vol. 15, No. 5, pp. 1592-1604. https://doi.org/10.1109/TASL.2007.899218
  7. Kim, T. & Attias, H. T. & Lee, S. Y. & Lee, T. W. (2007). Blind source separation exploiting higher-order frequency dependencies, Audio, Speech, and Language Processing, IEEE Transactions on. Vol. 15, pp. 70-79. https://doi.org/10.1109/TASL.2006.872618
  8. Chu, Z. H, & Bae, K. S. (2013). Post-processing of IVA-based 2-channel blind source separation for solving the frequency bin permutation problem. Malsori, Vol. 5, No. 4, 211-216 (추쯔하오, 배건성 (2013). IVA 기반의 2채널 암묵적신호분리에서 주파수빈 뒤섞임 문제 해결을 위한 후처리 과정. 말소리 제5권 제4호, 211-216) https://doi.org/10.13064/KSSS.2013.5.4.211
  9. Murata, N. & Ikeda, S. & Ziehe, A. (2001). An approach to blind source separation based on temporal structure of speech signals, Neurocomputing. Vol. 41, pp. 1-24. https://doi.org/10.1016/S0925-2312(00)00345-3
  10. Sawada, H. & Araki, S. & Makino, S. (2007). Measuring dependence of bin-wise separated signals for permutation alignment in frequency-domain BSS, ISCAS 2007. IEEE International Symposium on. pp. 3247-3250.
  11. Donohue, K. D. (2009) Audio Array Toolbox. http://www.engr.uky.edu/-donohue/audio/Arrays/MAToolbox.htm
  12. ITU-T. (2001) PESQ. http://www.itu.int/rec/T-REC-P.862/en

Cited by

  1. Improvement of convergence speed in FDICA algorithm with weighted inner product constraint of unmixing matrix vol.7, pp.4, 2015, https://doi.org/10.13064/KSSS.2015.7.4.017