An Efficient Separation for Convolutive Mixtures

Authors: Salah Al-Din I. Badran, Samad Ahmadi, Dylan Menzies, Ismail Shahin

Abstract:

This paper describes a new efficient blind source separation method; in this method we uses a non-uniform filter bank and a new structure with different sub-bands. This method provides a reduced permutation and increased convergence speed comparing to the full-band algorithm. Recently, some structures have been suggested to deal with two problems: reducing permutation and increasing the speed of convergence of the adaptive algorithm for correlated input signals. The permutation problem is avoided with the use of adaptive filters of orders less than the full-band adaptive filter, which operate at a sampling rate lower than the sampling rate of the input signal. The decomposed signals by analysis bank filter are less correlated in each sub-band than the input signal at full-band, and can promote better rates of convergence.

Keywords: Blind source separation (BSS), estimates, full-band, mixtures, Sub-band.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1092311

References:

[1] Batalheiro, P., Mariane R., Diego B., "Subband Blind Source Separation with Critically Sampled Filter Banks”, IWSSIP 2010 - 17th International Conference on Systems, Signals and Image Processing.
[2] Buchner, H., Aichner, R., Kellermann, W., "A Generalization of Blind Source separation Algorithms for Convolutive Mixtures Based on Second-Order Statistics”, IEEE Transaction on Speech and Audio Processing, Jan. 2005.
[3] Buchner, H., Aichner, R., Kellermann, W., "A Generalization of a Class of Blind Source Separation Algorithms for convolutive mixtures”. In: Proc. Int. Symposium Independent Component Analysis Blind Signal Separation, April 2003.
[4] Nesta, F., Omologo, M., Svaizer, P., "Multiple TDOA estimation by using a state coherence transform for solving the permutation problem in frequency-domain BSS”. In: Proc. Machine Learning for Signal Processing, October 2008.
[5] Aichner, R., Buchner, H., Kellermann,W., "Exploiting Narrowband Efficiency for Broadband Convolutive Blind Source Separation”, EURASIP Journal on Applied Signal Processing , pp. 1–9, September 2006.
[6] Douglas, S. C., Malay Gupta, "Scaled Natural Gradient Algorithms for Instantaneous and Convolutive Blind Source Separation”. In: Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, v. 2, pp.II-637 – II-640, April 2007.
[7] Araki, S., Makino, S., R. Aichner, et al., "Subband-Based Blind Separation for Convolutive Mixtures of speech”, IEICE Transaction Fundamentals, ver. E88-A, pp. 3593–3603, 2005
[8] Lee, I., Kim, T., Lee, T.W., "Independent vector analysis for convolutive blind speech separation”. Signals and Communication Technology, pp. 169-192. Springer Netherlands, 2007.
[9] Aichner, R., Buchner, H., Araki, S., et al., "On-Line Time-Domain Blind Source Separation of Nonstationary Convolved Signals”. In: Proc. Eur. Signal Processing Conf., pp. 987–992, April 2003.