{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T09:33:43Z","timestamp":1774690423271,"version":"3.50.1"},"reference-count":32,"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\/icassp49357.2023.10094687","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":10,"title":["Context-Aware Fine-Tuning of Self-Supervised Speech Models"],"prefix":"10.1109","author":[{"given":"Suwon","family":"Shon","sequence":"first","affiliation":[{"name":"ASAPP"}]},{"given":"Felix","family":"Wu","sequence":"additional","affiliation":[{"name":"ASAPP"}]},{"given":"Kwangyoun","family":"Kim","sequence":"additional","affiliation":[{"name":"ASAPP"}]},{"given":"Prashant","family":"Sridhar","sequence":"additional","affiliation":[{"name":"ASAPP"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Skip-thought vectors","volume":"28","author":"kiros","year":"2015","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.53"},{"key":"ref15","article-title":"ALBERT: A Lite BERT for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"ICLRE"},{"key":"ref14","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref30","article-title":"Speech summarization using restricted self-attention","author":"sharma","year":"2021"},{"key":"ref11","article-title":"Lebenchmark, un référentiel d’ évaluation pour le français oral","author":"le","year":"2022","journal-title":"JEP 2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1460"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747871"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1953"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003749"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10326"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746884"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3173"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1283"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11214"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053247"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1643"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagraniy","year":"2017","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref4","article-title":"Representation Learning with Contrastive Predictive Coding","author":"van den oord","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"}],"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\/10094687.pdf?arnumber=10094687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:41Z","timestamp":1700507261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094687","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}