{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T11:10:18Z","timestamp":1721301018613},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1704170","1743616"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Google Faculty Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2019.2959721","type":"journal-article","created":{"date-parts":[[2019,12,13]],"date-time":"2019-12-13T21:19:57Z","timestamp":1576271997000},"page":"646-655","source":"Crossref","is-referenced-by-count":9,"title":["Multi-Stream End-to-End Speech Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-2496-5224","authenticated-orcid":false,"given":"Ruizhi","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8837-401X","authenticated-orcid":false,"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Sri Harish","family":"Mallidi","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4560-8039","authenticated-orcid":false,"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8032-4811","authenticated-orcid":false,"given":"Hynek","family":"Hermansky","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-731"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref37","first-page":"11","article-title":"USTC-iFlytek system for CHiME-4 challenge","author":"du","year":"0","journal-title":"Proceedings of CHI 5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.07.014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2016.7602888"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref60","article-title":"Residual convolutional CTC networks for automatic speech recognition","author":"wang","year":"2017","journal-title":"arXiv 1702 07793"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1423"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.12.004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682650"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1655"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2414"},{"key":"ref58","article-title":"Improved regularization techniques for end-to-end speech recognition","author":"zhou","year":"2017","journal-title":"arXiv 1712 07108"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref54","article-title":"CSR-II (WSJ1) complete","volume":"ldc94s13a","author":"consortium","year":"0","journal-title":"Proc Linguist Data Consortium"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref52","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-751"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref40","article-title":"Stream attention for far-field multi-microphone ASR","author":"wang","year":"2017","journal-title":"arXiv 1711 11141"},{"key":"ref12","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","author":"raffel","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","article-title":"Monotonic chunkwise attention","author":"chiu","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref17","article-title":"A practical and efficient multistream framework for noise robust speech recognition","author":"mallidi","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236871"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472765"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref3","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref7","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn Workshop Represent Learn"},{"key":"ref49","article-title":"Supervised sequence labelling with recurrent neural networks","author":"graves","year":"2008"},{"key":"ref9","first-page":"431","article-title":"Local monotonic attention mechanism for end-to-end speech and language processing","author":"tjandra","year":"0","journal-title":"Proc Int Joint Conf Natural Lang Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1301"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764276"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1536"},{"key":"ref47","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202473"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404806"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-5"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/8938144\/8932598-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08932598.pdf?arnumber=8932598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:21Z","timestamp":1651080681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8932598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2959721","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}