{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:26:13Z","timestamp":1740147973578,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"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 J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/jstsp.2017.2764276","type":"journal-article","created":{"date-parts":[[2017,10,18]],"date-time":"2017-10-18T18:28:32Z","timestamp":1508351312000},"page":"1274-1288","source":"Crossref","is-referenced-by-count":56,"title":["Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5422-6617","authenticated-orcid":false,"given":"Tsubasa","family":"Ochiai","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4560-8039","authenticated-orcid":false,"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366923"},{"key":"ref33","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2528171"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-92"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2325781"},{"key":"ref35","first-page":"1","article-title":"Recurrent models for auditory attention in multi-microphone distance speech recognition","author":"kim","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832988"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref40","article-title":"Wide\n residual BLSTM network with discriminative speaker adaptation for robust speech recognition","author":"heymann","year":"2016","journal-title":"Proc CHiME 2016 Workshop"},{"key":"ref11","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition\n in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-173"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952160"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref18","first-page":"26","article-title":"A study of learning based beamforming methods for speech recognition","author":"xiao","year":"2016","journal-title":"Proc CHiME 2016 Workshop"},{"key":"ref19","article-title":"Multi-channel speech recognition: LSTMs all\n the way through","author":"erdogan","year":"0","journal-title":"Proc CHiME 2016 Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898454"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref29","first-page":"2632","article-title":"Multichannel end-to-end speech\n recognition","author":"ochiai","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"article-title":"End-to-end continuous speech recognition\n using attention-based recurrent NN: First results","year":"2014","author":"chorowski","key":"ref2"},{"key":"ref9","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref46","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref45","first-page":"15","article-title":"The matrix cookbook","volume":"7","author":"petersen","year":"2008","journal-title":"Kongens Lyngby Denmark Technical University of Denmark"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952756"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"article-title":"ADADELTA: An adaptive learning rate method","year":"2012","author":"zeiler","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952119"},{"key":"ref41","article-title":"Chainer: A next-generation open source\n framework for deep learning","author":"tokui","year":"2015","journal-title":"Proc NIPS Workshop Mach Learn Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952163"},{"key":"ref44","first-page":"3104","article-title":"Sequence to\n sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref43","first-page":"1310","article-title":"On the\n difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.7278"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8103432\/08070987.pdf?arnumber=8070987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:59:46Z","timestamp":1642006786000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8070987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":47,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2017.2764276","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}