{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:55:03Z","timestamp":1776887703019,"version":"3.51.2"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097139","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":25,"title":["Adapting Self-Supervised Models to Multi-Talker Speech Recognition Using Speaker Embeddings"],"prefix":"10.1109","author":[{"given":"Zili","family":"Huang","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desh","family":"Raj","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola","family":"Garc\u00eda","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and Human Language Technology Center of Excellence,Baltimore,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/JSTSP.2019.2922820","article-title":"SpeakerBeam: Speaker aware neural network for target speaker extraction in speech mixtures","volume":"13","author":"\u017emol\u00edkov\u00e1","year":"2019","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-91","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: Insights for automatic speech recognition","author":"\u00e7etin","year":"2006","journal-title":"InterSpeech"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.427"},{"key":"ref19","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref25","first-page":"1","article-title":"Chime-6 challenge: Tackling multi-speaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020","journal-title":"Proc The 6th International Workshop on Speech Processing in Everyday Environments (CHiME 2020)"},{"key":"ref20","article-title":"Conditionally adaptive multi-task learning: Improving transfer learning in NLP using fewer parameters & less data","author":"pilault","year":"2020","journal-title":"ICLRE"},{"key":"ref22","article-title":"The AMI meeting corpus: A preannouncement","author":"carletta","year":"2005","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"key":"ref21","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref29","article-title":"Front-end factor analysis for speaker verification","author":"dehak","year":"2010","journal-title":"IEEE TASLP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097139.pdf?arnumber=10097139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:39Z","timestamp":1699883979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097139","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}