{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T07:49:18Z","timestamp":1725781758499},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053455","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7014-7018","source":"Crossref","is-referenced-by-count":4,"title":["A Practical Two-Stage Training Strategy for Multi-Stream End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ruizhi","family":"Li","sequence":"first","affiliation":[]},{"given":"Gregory","family":"Sell","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Hynek","family":"Hermansky","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"article-title":"Regularizing neural networks by penalizing confident output distributions","year":"2017","author":"pereyra","key":"ref32"},{"key":"ref31","article-title":"Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling","author":"cho","year":"2018","journal-title":"Proc of SLT"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc of ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref16","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","author":"chan","year":"2015","journal-title":"Proc of ICASSP"},{"key":"ref17","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref18","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc ICML Workshop on Representation Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref28","first-page":"28","article-title":"The ami meeting corpus: A preannouncement","author":"carletta","year":"2005","journal-title":"Proc of MLMI"},{"key":"ref4","article-title":"Coding and decoding of messages in human speech communication: Implications for machine recognition of speech","author":"hermansky","year":"2018","journal-title":"Speech Communication"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-731"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472765"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1037"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236871"},{"journal-title":"CHiME-5","article-title":"Channel selection using neural network posterior probability for speech recognition with distributed microphone arrays in everyday environments","year":"2018","key":"ref9"},{"key":"ref1","article-title":"A Practical and Efficient Multistream Framework for Noise Robust Speech Recognition","author":"reddy mallidi","year":"2018","journal-title":"Ph D thesis"},{"key":"ref20","first-page":"4835","article-title":"Joint CTCattention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"Proc of ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref24","article-title":"Multi-encoder multi-resolution framework for end-to-end speech recognition","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1811 04897"},{"key":"ref23","article-title":"Multi-stream end-toend speech recognition","author":"li","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref26","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref25","first-page":"7105","article-title":"Stream attentionbased multi-array end-to-end speech recognition","author":"wang","year":"2019","journal-title":"Proc of ICASSP"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053455.pdf?arnumber=9053455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:44Z","timestamp":1656375104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053455\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053455","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}