[{"department":[{"_id":"54"}],"type":"conference","related_material":{"link":[{"description":"Poster","relation":"supplementary_material","url":"https://groups.uni-paderborn.de/nt/pubs/2017/icassp_2017_heymann_poster.pdf"}]},"title":"BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System","date_updated":"2019-08-13T12:57:53Z","year":"2017","user_id":"40767","_id":"11809","language":[{"iso":"eng"}],"publication":"Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)","citation":{"bibtex":"@inproceedings{Heymann_Drude_Boeddeker_Hanebrink_Haeb-Umbach_2017, title={BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System}, booktitle={Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)}, author={Heymann, Jahn and Drude, Lukas and Boeddeker, Christoph and Hanebrink, Patrick and Haeb-Umbach, Reinhold}, year={2017} }","chicago":"Heymann, Jahn, Lukas Drude, Christoph Boeddeker, Patrick Hanebrink, and Reinhold Haeb-Umbach. “BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System.” In <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2017.","apa":"Heymann, J., Drude, L., Boeddeker, C., Hanebrink, P., &#38; Haeb-Umbach, R. (2017). BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System. In <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>.","ama":"Heymann J, Drude L, Boeddeker C, Hanebrink P, Haeb-Umbach R. BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System. In: <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2017.","ieee":"J. Heymann, L. Drude, C. Boeddeker, P. Hanebrink, and R. Haeb-Umbach, “BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System,” in <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2017.","short":"J. Heymann, L. Drude, C. Boeddeker, P. Hanebrink, R. Haeb-Umbach, in: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.","mla":"Heymann, Jahn, et al. “BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System.” <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2017."},"status":"public","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2017/icassp_2017_heymann_paper.pdf"}],"author":[{"full_name":"Heymann, Jahn","last_name":"Heymann","id":"9168","first_name":"Jahn"},{"first_name":"Lukas","id":"11213","last_name":"Drude","full_name":"Drude, Lukas"},{"first_name":"Christoph","id":"40767","last_name":"Boeddeker","full_name":"Boeddeker, Christoph"},{"full_name":"Hanebrink, Patrick","last_name":"Hanebrink","first_name":"Patrick"},{"first_name":"Reinhold","id":"242","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"oa":1,"date_created":"2019-07-12T05:28:40Z","abstract":[{"lang":"eng","text":"This paper presents an end-to-end training approach for a beamformer-supported multi-channel ASR system. A neural network which estimates masks for a statistically optimum beamformer is jointly trained with a network for acoustic modeling. To update its parameters, we propagate the gradients from the acoustic model all the way through feature extraction and the complex valued beamforming operation. Besides avoiding a mismatch between the front-end and the back-end, this approach also eliminates the need for stereo data, i.e., the parallel availability of clean and noisy versions of the signals. Instead, it can be trained with real noisy multichannel data only. Also, relying on the signal statistics for beamforming, the approach makes no assumptions on the configuration of the microphone array. We further observe a performance gain through joint training in terms of word error rate in an evaluation of the system on the CHiME 4 dataset."}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}]}]