{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:24:54Z","timestamp":1776889494090,"version":"3.51.2"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/taslp.2017.2672401","type":"journal-article","created":{"date-parts":[[2017,2,20]],"date-time":"2017-02-20T19:09:34Z","timestamp":1487617774000},"page":"965-979","source":"Crossref","is-referenced-by-count":182,"title":["Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition"],"prefix":"10.1109","volume":"25","author":[{"given":"Tara N.","family":"Sainath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin W.","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Variani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michiel","family":"Bacchiani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Izhak","family":"Shafran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Senior","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kean","family":"Chin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ananya","family":"Misra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"3274","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178925"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-173"},{"key":"ref37","first-page":"1","article-title":"Gated feedback recurrent neural networks","author":"chung","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853583"},{"key":"ref35","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-84"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947700"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7496.003.0016","article-title":"Scaling Learning Algorithms Towards AI","author":"bengio","year":"2007","journal-title":"Large-Scale Kernel Machines"},{"key":"ref11","first-page":"1766","article-title":"Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks","author":"palaz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"890","article-title":"Acoustic modeling with deep neural networks using raw time signal for LVCSR","author":"t\u00fcske","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref15","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","first-page":"30","article-title":"Speaker localization and microphone spacing invariant acoustic modeling from raw multichannel waveforms","author":"sainath","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1982.1142739"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404836"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref3","first-page":"1","article-title":"Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the REVERB challenge","author":"delcroix","year":"0","journal-title":"Proc REVERB Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-92"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_42"},{"key":"ref8","first-page":"1","article-title":"Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures","author":"hershey","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832988"},{"key":"ref2","author":"benesty","year":"2009","journal-title":"Microphone Array Signal Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288863"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-04619-7","author":"brandstein","year":"2001","journal-title":"Microphone Arrays Signal Processing Techniques and Applications"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref21","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1459"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854672"},{"key":"ref41","author":"bracewell","year":"1999","journal-title":"The Fourier Transform and Its Applications"},{"key":"ref23","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref44","first-page":"529","article-title":"Broadband maximum energy array with user imposed spatial and frequency constraints","author":"d","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472644"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881676"},{"key":"ref25","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7895265\/07859320.pdf?arnumber=7859320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:39:46Z","timestamp":1749998386000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7859320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":44,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2672401","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}