Multichannel blind source separation based on non-negative tensor factorization in wavenumber domain

Yuki Mitsufuji, Shoichi Koyama, Hiroshi Saruwatari

Abstract

Multichannel non-negative matrix factorization based on a spatial covariance model is one of the most promising techniques for blind source separation. However, this approach is not tractable for a large number of microphones, M, because the computational cost is of order O(M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> ) per time-frequency bin. To circumvent this drawback, we propose non-negative tensor factorization in the wavenumber domain, which reduces the cost to the order O(M). It transforms microphone signals into the spatial frequency domain, a technique that is commonly used for soundfield reconstruction. The proposed method is compared to several blind source separation (BSS) methods in terms of separation quality and computational cost.
BibTeX
@inproceedings{mitsufuji2016multichannel,
  author = {Yuki Mitsufuji and Shoichi Koyama and Hiroshi Saruwatari},
  title = {{Multichannel blind source separation based on non-negative tensor factorization in wavenumber domain}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2016},
  doi = {10.1109/icassp.2016.7471636},
}

Loading related content...

Figure