Convolutive Blind Separation Using Domino Effect Relevance Ranking

Abstract:

Based on the discovery that there is a good amplitude correlation between neighbour bins of non-stationary signals, we presented a new blind source separation method using Domino Effect relevance ranking that can eliminate the permutation indeterminacy. Since there is no complicated mathematic derivation in this method, it is relatively simple in theory. Furthermore, the outcome of simulation experiments confirmed its validity in blind source separation of communication signals such as QPSK signal. In addition, this method is robust and time saving.

• Periodical: Advanced Materials Research (Volumes 774-776)
• Pages: 1699-1702
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.774-776.1699
• Online since: September 2013
• Authors: Peng Fei Xu
• Keywords: Amplitude Correlation, Blind Signal Separation, Communication Signals, Neighbour Bins

References

[1] S. Araki, S. Makino, T. Nishikawa, and H. Saruwatari, Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech, in Proc. ICASSP2001, 2001, MULT-P2. 3.

DOI: 10.1109/icassp.2001.940212

[2] R. Mukai, S. Araki, and S. Makino, Separation and dereverberation performance of frequency domain blind source separation for speech in a reverberant environment, in Proc. Eurospeech2001, Sept. (2001).

DOI: 10.21437/eurospeech.2001-608

[3] Murata N., Ikeda S. and Ziehe A. An approach to blind source separation based on temporal structure of speech signals. Neurocomput, 2001, 41(1-4): 1-24.

DOI: 10.1016/s0925-2312(00)00345-3

[4] JIANG Wei-dong, LU Ji-ren．Blind source separation of speech signals based on the amplitude correlation of neighbour bins [J]. Journal of circuits and systems. 2005(03): 1-4.

[5] J. F. Cardoso, JADE algorithm, , Matlab code available at http: /www. tsi. enst. fr/~cardoso/guidesepsou. html.