Robust real-time blind source separation for moving speakers in a room

Ryo Mukai, Hiroshi Sawada, Shoko Araki, Shoji Makino

Abstract

This paper describes a robust real-time blind source separation (BSS) method for moving speech signals in a room. Our method employs frequency domain independent component analysis (ICA) using a blockwise batch algorithm in the first stage, and the separated signals are refined by postprocessing using crosstalk component estimation and nonstationary spectral subtraction in the second stage. The blockwise batch algorithm achieves better performance than an online algorithm when sources are fixed, and the postprocessing compensates for performance degradation caused by source movement. Experimental results using speech signals recorded in a real room show that the proposed method realizes robust real-time separation for moving sources. Our method is implemented on a standard PC and works in real time.
BibTeX
@inproceedings{mukai2003robust,
  author = {Ryo Mukai and Hiroshi Sawada and Shoko Araki and Shoji Makino},
  title = {{Robust real-time blind source separation for moving speakers in a room}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2003},
  doi = {10.1109/icassp.2003.1200008},
}

Loading related content...

Figure