# A SIMPLE AND COMUTATIONALLY EFFICIENT ALGORITHM FOR REAL-TIME BLIND SOURCE SEPARATION OF SPEECH MIXTURES

### Tarig Ballal, Nedelko Grbic, Abbas Mohammed

#### Abstract

In this paper we exploit the amplitude diversity provided by two sensors to achieve blind separation of two speech sources. We propose a simple and highly computationally efficient method for separating sources that are W-disjoint orthogonal (W-DO), that are sources whose time-frequency representations are disjoint sets. The Degenerate Unmixing and Estimation Technique (DUET), a powerful and efficient method that exploits the W-disjoint orthogonality property, requires extensive computations for maximum likehood parameter learning. Our proposed method avoids all the computations required for parameters estimation by assuming that the sources are "cross high-low diverse (CH-LD)", an assumption that is explained later and that can be satisfied exploiting the sensors settings/directions. With this assumption and the W-disjoint orthogonality property, two binary time-frequency masks that can extract the original sources from one of the two mixtures, can be constructed directly from the amplitude ratios of the time-frequency points of the two mixtures. The method works very well when tested with both artificial and real mixtures. Its performance is comparable to DUET, and it requires only 2% of the computations required by the DUET method. Moreover, it is free of convergence problems that lead to poor SIR ratios in the first parts of the signals. As with all binary masking approaches, the method suffers from artifacts that appear in the output signals.

#### References

- Cardoso, J.-F., 1998. Blind Signal Separation: Statistical Principles. In Proceedings of the IEEE, vol. 86, no. 10, pp. 2009-2025.
- Bell, A.J. and Sejnowski, T.J., 1995. An Information Maximization Approach to Blind Separation and Blind Deconvolution. Neural Computation, pp. 1129-1 159.
- Weinstein, E., Feder, M. and Oppenheim, A., 1993 Multichannel Signal Separation by Decorrelation. IEEE Transaction on Speech and Audio Processing, vol. 1, no. 4, pp. 405-413.
- Parra, L. and Spence, C., 2000. Convolutive Blind Source Separation Based On Multiple Decorrelations. IEEE Transactions on Speech and Audio Processing, March 2000.
- Broman, H., Lindgren, U., Sahlin, H and Stoica, P, 1999. Source Separation: A TITO System Identification Approach. Signal Processing, vol. 73, pp. 169-183.
- Jourjine, A., Rickard, S. and Yilmaz, O., 2000. Blind Separation of Disjoint Orthogonal Signals: Demixing N Sources from 2 Mixtures. Proceedings of the 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey.
- Rickard, S., Balan, R. and Rosca, J., 2001. Real- Time Time-Frequency Based Blind Source Separation. Proceedings of the International Workshop of Independent Component Analysis and Blind Source Separation, San Diego, CA.
- Yilmaz, O Rickard, S, July 2004. Blind Separation of Speech Mixtures via Time-Frequency Masking. IEEE Transactions on Signal Processing, Vol. 52.
- Bofill, P. and Zibulevsky, M., 2000. Blind Separation of More Sources than Mixtures Using Sparsity of Their Short-time Fourier Transform. International Workshop on Independent Component Analysis and Blind Signal Separation, Helsinki, Finland.
- Allen, Jont B., June1977. Short Term Spectral Analysis, Synthesis and Modification by Discrete Fourier Transform. IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 25.
- Araki, S., Makino, S., Sawada H. and Mukai, R., Sept. 2004. Underdetermined Blind Separation of Convolutive Mixtures of Speech with Directivity Pattern Based Mask and ICA. ICA2004 (Fifth International Conference on Independent Component Analysis and Blind Signal Separation), pp. 898-905.
- http://inc2.ucsd.edu/tewon/

#### Paper Citation

#### in Harvard Style

Ballal T., Grbic N. and Mohammed A. (2006). **A SIMPLE AND COMUTATIONALLY EFFICIENT ALGORITHM FOR REAL-TIME BLIND SOURCE SEPARATION OF SPEECH MIXTURES** . In *Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2006)* ISBN 978-972-8865-64-1, pages 105-109. DOI: 10.5220/0001571901050109

#### in Bibtex Style

@conference{sigmap06,

author={Tarig Ballal and Nedelko Grbic and Abbas Mohammed},

title={A SIMPLE AND COMUTATIONALLY EFFICIENT ALGORITHM FOR REAL-TIME BLIND SOURCE SEPARATION OF SPEECH MIXTURES},

booktitle={Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2006)},

year={2006},

pages={105-109},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0001571901050109},

isbn={978-972-8865-64-1},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2006)

TI - A SIMPLE AND COMUTATIONALLY EFFICIENT ALGORITHM FOR REAL-TIME BLIND SOURCE SEPARATION OF SPEECH MIXTURES

SN - 978-972-8865-64-1

AU - Ballal T.

AU - Grbic N.

AU - Mohammed A.

PY - 2006

SP - 105

EP - 109

DO - 10.5220/0001571901050109