{"author":[{"first_name":"Lukas","last_name":"Drude","full_name":"Drude, Lukas","id":"11213"},{"first_name":"Daniel","full_name":"Hasenklever, Daniel","last_name":"Hasenklever"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"title":"Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation","status":"public","citation":{"mla":"Drude, Lukas, et al. “Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation.” <i>ICASSP 2019, Brighton, UK</i>, 2019.","short":"L. Drude, D. Hasenklever, R. Haeb-Umbach, in: ICASSP 2019, Brighton, UK, 2019.","apa":"Drude, L., Hasenklever, D., &#38; Haeb-Umbach, R. (2019). Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation. In <i>ICASSP 2019, Brighton, UK</i>.","ieee":"L. Drude, D. Hasenklever, and R. Haeb-Umbach, “Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation,” in <i>ICASSP 2019, Brighton, UK</i>, 2019.","chicago":"Drude, Lukas, Daniel Hasenklever, and Reinhold Haeb-Umbach. “Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation.” In <i>ICASSP 2019, Brighton, UK</i>, 2019.","bibtex":"@inproceedings{Drude_Hasenklever_Haeb-Umbach_2019, title={Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation}, booktitle={ICASSP 2019, Brighton, UK}, author={Drude, Lukas and Hasenklever, Daniel and Haeb-Umbach, Reinhold}, year={2019} }","ama":"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."},"file_date_updated":"2019-08-14T07:19:13Z","oa":"1","publication":"ICASSP 2019, Brighton, UK","abstract":[{"lang":"eng","text":"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."}],"department":[{"_id":"54"}],"has_accepted_license":"1","year":"2019","file":[{"access_level":"open_access","file_id":"12925","file_size":368225,"creator":"huesera","date_created":"2019-08-14T07:19:13Z","content_type":"application/pdf","relation":"main_file","file_name":"ICASSP_2019_Drude_Paper.pdf","date_updated":"2019-08-14T07:19:13Z"}],"type":"conference","date_updated":"2022-01-06T06:51:21Z","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"language":[{"iso":"eng"}],"date_created":"2019-07-23T07:37:54Z","ddc":["000"],"_id":"12874","user_id":"59789"}