About this Journal Submit a Manuscript Table of Contents
Advances in Acoustics and Vibration
Volume 2011 (2011), Article ID 765429, 10 pages
http://dx.doi.org/10.1155/2011/765429
Research Article

Improved Method of Blind Speech Separation with Low Computational Complexity

1Corporate Research & Development Center, Yamaha Corporation, 203 Matsunokijima, Iwata 438-0192, Japan
2Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma 630-0192, Japan
3Graduate School of Engineering, Mie University, 1577, Kurimamachiya-cho, Tsu 514-8507, Japan
4Graduate School of Information Science, Nagoya University, Chikusa-ku Furou-cho, Nagoya 464-8601, Japan

Received 15 June 2011; Accepted 19 July 2011

Academic Editor: K. M. Liew

Copyright © 2011 Kazunobu Kondo et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

A blind speech separation method with low computational complexity is proposed. This method consists of a combination of independent component analysis with frequency band selection, and a frame-wise spectral soft mask method based on an interchannel power ratio of tentative separated signals in the frequency domain. The soft mask cancels the transfer function between sources and separated signals. A theoretical analysis of selection criteria and the soft mask is given. Performance and effectiveness are evaluated via source separation simulations and a computational estimate, and experimental results show the significantly improved performance of the proposed method. The segmental signal-to-noise ratio achieves 7 [dB] and 3 [dB], and the cepstral distortion achieves 1 [dB] and 2.5 [dB], in anechoic and reverberant conditions, respectively. Moreover, computational complexity is reduced by more than 80% compared with unmodified FDICA.