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