{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:18:59Z","timestamp":1780773539418,"version":"3.54.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000646","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["JP21J21371"],"award-info":[{"award-number":["JP21J21371"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001695","name":"JST","doi-asserted-by":"publisher","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}],"id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003382","name":"CREST","doi-asserted-by":"publisher","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023199","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"260-265","source":"Crossref","is-referenced-by-count":14,"title":["End-to-End Integration of Speech Recognition, Dereverberation, Beamforming, and Self-Supervised Learning Representation"],"prefix":"10.1109","author":[{"given":"Yoshiki","family":"Masuyama","sequence":"first","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Università Politecnica delle Marche,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobutaka","family":"Ono","sequence":"additional","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"6","key":"ref1","first-page":"82","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"26","author":"H","year":"2012","journal-title":"IEEE SPM"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref5","article-title":"Attention-based models for speech recognition","volume-title":"Proc. NIPS","author":"Chorowski"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","volume-title":"Sequence transduction with recurrent neural net-works","author":"Graves","year":"2012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746220"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-519"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"issue":"7","key":"ref21","article-title":"A summary of the REVERB chal-lenge: State-of-the-art and remaining challenges in reverber-ant speech processing research","author":"Kinoshita","year":"2016","journal-title":"EURASIP JASP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1768"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2911179"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2432"},{"key":"ref27","first-page":"817","article-title":"WPD++: An improved neural beamformer for si-multaneous speech separation and dereverberation","volume-title":"Proc. SLT","author":"Ni"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref29","article-title":"Multichannel end-to-end speech recognition","volume-title":"Proc. ICML","author":"Ochiai"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937250"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746678"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414661"},{"key":"ref35","author":"Gu","year":"2019","journal-title":"End-to-end multi-channel speech separation"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3145319"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632720"},{"key":"ref38","first-page":"7669","article-title":"Libri-light: A benchmark for ASR with limited or no supervision","volume-title":"Proc. ICA SSP","author":"Khan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10727"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2007.902460"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref46","article-title":"The USTC-iFlytek system for CHiME-4 chal-lenge","author":"Du","year":"2016","journal-title":"CHiME"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"issue":"60","key":"ref49","article-title":"Strategies for distant speech recognition in reverberant environments","author":"Delcroix","year":"2015","journal-title":"EURASIP JASP"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023199.pdf?arnumber=10023199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:35:45Z","timestamp":1707806145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023199\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023199","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}