@inproceedings{12874,
  abstract     = {{We propose a training scheme to train neural network-based source separation algorithms from scratch when parallel clean data is unavailable. In particular, we demonstrate that an unsupervised spatial clustering algorithm is sufficient to guide the training of a deep clustering system. We argue that previous work on deep clustering requires strong supervision and elaborate on why this is a limitation. We demonstrate that (a) the single-channel deep clustering system trained according to the proposed scheme alone is able to achieve a similar performance as the multi-channel teacher in terms of word error rates and (b) initializing the spatial clustering approach with the deep clustering result yields a relative word error rate reduction of 26% over the unsupervised teacher.}},
  author       = {{Drude, Lukas and Hasenklever, Daniel and Haeb-Umbach, Reinhold}},
  booktitle    = {{ICASSP 2019, Brighton, UK}},
  title        = {{{Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation}}},
  year         = {{2019}},
}