{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:24:32Z","timestamp":1776889472397,"version":"3.51.2"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472778","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5745-5749","source":"Crossref","is-referenced-by-count":126,"title":["Deep beamforming networks for multi-channel speech recognition"],"prefix":"10.1109","author":[{"given":"Xiong","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Hakan","family":"Erdogan","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"John","family":"Hershey","sequence":"additional","affiliation":[]},{"given":"Michael L.","family":"Seltzer","sequence":"additional","affiliation":[]},{"given":"Guoguo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Mandel","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-015-0245-7"},{"key":"ref11","volume":"1","author":"benesty","year":"2008","journal-title":"Microphone Array Signal Processing"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/TSA.2004.832988","article-title":"Likelihood-maximizing beamforming for robust hands-free speech recognition","volume":"12","author":"michael","year":"2004","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref13","article-title":"Speech acoustic modeling from raw multichannel waveforms","author":"yedid","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854663"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref17","first-page":"2814","article-title":"A learning-based approach to direction of arrival estimation in noisy and reverberant environments","author":"xiong","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","first-page":"81","article-title":"WSJ-CAM0: a british english speech corpus for large vocabulary continuous speech recognition","author":"robinson","year":"1995","journal-title":"Proceeding of ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404843"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00030-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90019-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"29","author":"geoffrey","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9780470714089"},{"key":"ref20","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref21","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014","journal-title":"Tech Rep"},{"key":"ref23","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","author":"vesely","year":"2013","journal-title":"InterSpeech"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472778.pdf?arnumber=7472778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T17:00:17Z","timestamp":1498323617000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472778","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}