Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation

Zhong-Qiu Wang, Jonathan Le Roux, John R. HersheyICASSP 2018 · OpenReview

Abstract

The recently-proposed deep clustering algorithm represents a fundamental advance towards solving the cocktail party problem in the single-channel case. When multiple microphones are available, spatial information can be leveraged to differentiate signals from different directions. This study combines spectral and spatial features in a deep clustering framework so that the complementary spectral and spatial information can be simultaneously exploited to improve speech separation. We find that simply encoding inter-microphone phase patterns as additional input features during deep clustering provides a significant improvement in separation performance, even with random microphone array geometry. Experiments on a spatial-ized version of the wsj0-2mix dataset show the strong potential of the proposed algorithm for speech separation in reverberant environments.
BibTeX
@inproceedings{wang2018multi,
  author = {Zhong-Qiu Wang and Jonathan Le Roux and John R. Hershey},
  title = {{Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2018},
  url = {https://openreview.net/forum?id=eB3fLCeWOW},
}

Loading related content...

Figure