Multistage SIMO-Model-Based Blind Source Separation Combining Frequency-Domain ICA and Time-Domain ICA

Satoshi Ukai, Tomoya Takatani, Hiroshi Saruwatari, Kiyohiro Shikano, Ryo Mukai, Hiroshi Sawada

Abstract

In this paper, single-input multiple-output (SIMO)-model-based blind source separation (BSS) is addressed, where unknown mixed source signals are detected at microphones, and can be separated, not into monaural source signals but into SIMO-model-based signals from independent sources as they are at the microphones. This technique is highly applicable to high-fidelity signal processing such as binaural signal processing. First, we provide an experimental comparison between two kinds of SIMO-model-based BSS methods, namely, conventional frequency-domain ICA with projection-back processing (FDICA-PB), and SIMO-ICA which was recently proposed by the authors. Secondly, we propose a new combination technique of the FDICA-PB and SIMO-ICA, which can achieve a higher separation performance than the two methods. The experimental results reveal that the accuracy of the separated SIMO signals in the simple SIMO-ICA is inferior to that of the signals obtained by FDICA-PB under low-quality initial value conditions, but the proposed combination technique can outperform both simple FDICA-PB and SIMO-ICA.
BibTeX
@inproceedings{ukai2004multistage,
  author = {Satoshi Ukai and Tomoya Takatani and Hiroshi Saruwatari and Kiyohiro Shikano and Ryo Mukai and Hiroshi Sawada},
  title = {{Multistage SIMO-Model-Based Blind Source Separation Combining Frequency-Domain ICA and Time-Domain ICA}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2004},
  doi = {10.1109/icassp.2004.1326775},
}

Loading related content...

Figure