{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:30Z","timestamp":1740132870221,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2138259","tel:2138286","tel:2138307","tel:2137603","tel:2138296"],"award-info":[{"award-number":["2138259","tel:2138286","tel:2138307","tel:2137603","tel:2138296"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3449218","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T17:41:43Z","timestamp":1724694103000},"page":"2850-2854","source":"Crossref","is-referenced-by-count":0,"title":["MC-Whisper: Extending Speech Foundation Models to Multichannel Distant Speech Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5221-5412","authenticated-orcid":false,"given":"Xuankai","family":"Chang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2388-5935","authenticated-orcid":false,"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9170-0335","authenticated-orcid":false,"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[{"name":"LY Corporation, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Maekaku","sequence":"additional","affiliation":[{"name":"LY Corporation, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref5","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref7","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref11","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205285"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210879"},{"key":"ref26","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ochiai","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-552"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747146"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914704"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2756439"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682576"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023199"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447750"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref36","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"issue":"1","key":"ref37","first-page":"3","article-title":"Announcing the AMI meeting corpus","volume":"11","author":"Carletta","year":"2006","journal-title":"ELRA Newslett."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683294"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2918706"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/97\/10380231\/10645750-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10380231\/10645750.pdf?arnumber=10645750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:02:05Z","timestamp":1732669325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3449218","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2024]]}}}