Variational EM for binaural sound-source separation and localization

Antoine Deleforge, Florence Forbes, Radu Horaud

Abstract

The sound-source separation and localization (SSL) problems are addressed within a unified formulation. Firstly, a mapping between white-noise source locations and binaural cues is estimated. Secondly, SSL is solved via Bayesian inversion of this mapping in the presence of multiple sparse-spectrum emitters (such as speech), noise and reverberations. We propose a variational EM algorithm which is described in detail together with initialization and convergence issues. Extensive real-data experiments show that the method outperforms the state-of-the-art both in separation and localization (azimuth and elevation).
BibTeX
@inproceedings{deleforge2013variational,
  author = {Antoine Deleforge and Florence Forbes and Radu Horaud},
  title = {{Variational EM for binaural sound-source separation and localization}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  doi = {10.1109/icassp.2013.6637612},
}

Loading related content...

Figure