An Approach to Solving a Permutation Problem of Frequency Domain Independent Component Analysis for Blind Source Separation of Speech Signals

Independent component analysis (ICA) in the frequency domain is used for solving the problem of blind source separation (BSS). However, this method has some problems. For example, a general ICA algorithm cannot determine the permutation of signals which is important in the frequency domain ICA. In this paper, we propose an approach to the solution for a permutation problem. The idea is to effectively combine two conventional approaches. This approach improves the signal separation performance by exploiting features of the conventional approaches. We show the simulation results using artificial data.

Authors:

• Masaru Fujieda
• Takahiro Murakami
• Yoshihisa Ishida

Keywords:

• Blind source separation
• Independent componentanalysis
• Frequency domain
• Permutation ambiguity.

References:

[1] N. Murata, S. Ikeda, A. Ziehe, "An approach to blind source separation
based on temporal structure of speech signals," in Neurocomputing, 41,
2001, pp. 1-24.
[2] F. Asano, S. Ikeda, M. Ogawa, H. Asoh, N. Kitawaki, "Combined
approach of array processing and independent component analysis for
blind separation of acoustic signals," in IEEE trans. Speech and Audio
Processing, 11, No. 3, 2003, pp. 204-214.
[3] S. Kurita, H. Saruwatari, S. Kajita, K. Takeda, F. Itakura, "Evaluation of
blind signal separation method using directivity pattern under reverberant
conditions," in Proceedings of IEEE International Conference on
Acoustics, Speech, and Signal Processing, SAM-P2-5, Jun. 2000, pp.
3140-3143
[4] A. Hyvärinen, E. Oja, "Independent component analysis: a tutorial," in
Helsinki University of Technology, Laboratory of computer and
Information Science, Apr. 1999
[5] N. Murata, S. Ikeda, "An on-line algorithm for blind source separation on
speech signals," in Proceedings NOLTA'98, Sep. 1998, pp. 923-926.
[6] S. Araki, R. Mukai, S. Makino, T. Nishikawa, H. Saruwatari, "The
fundamental limitation of frequency domain blind source separation for
convolutive mixtures of speech," in IEEE Trans. Speech and Audio
Processing, 11, No. 2, 2003, pp. 109-116.