{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:42:59Z","timestamp":1776883379228,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446893","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11156-11160","source":"Crossref","is-referenced-by-count":3,"title":["Generative Context-Aware Fine-Tuning of Self-Supervised Speech Models"],"prefix":"10.1109","author":[{"given":"Suwon","family":"Shon","sequence":"first","affiliation":[{"name":"ASAPP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwangyoun","family":"Kim","sequence":"additional","affiliation":[{"name":"ASAPP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prashant","family":"Sridhar","sequence":"additional","affiliation":[{"name":"ASAPP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Te","family":"Hsu","sequence":"additional","affiliation":[{"name":"ASAPP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1643"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053247"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746884"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10326"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-552"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095204"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094687"},{"key":"ref10","article-title":"Stable beluga models","author":"Mahan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref15","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref16","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref17","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Deber-tav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2021"},{"issue":"1","key":"ref19","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446893.pdf?arnumber=10446893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:27:13Z","timestamp":1722576433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446893\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446893","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}