Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation Drude, Lukas Hasenklever, Daniel Haeb-Umbach, Reinhold ddc:000 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. 2019 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://ris.uni-paderborn.de/record/12874 https://ris.uni-paderborn.de/download/12874/12925 Drude L, Hasenklever D, Haeb-Umbach R. Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation. In: <i>ICASSP 2019, Brighton, UK</i>. ; 2019. eng info:eu-repo/semantics/openAccess