{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:17Z","timestamp":1776885497545,"version":"3.51.2"},"reference-count":30,"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":"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":"Huawei Noah's Ark Lab"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091302006"],"award-info":[{"award-number":["ZDSYS20230626091302006"]}]},{"name":"Shenzhen Science and Technology Research Fund"},{"name":"Fundamental Research Key Project","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3438541","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T18:23:53Z","timestamp":1722882233000},"page":"2055-2059","source":"Crossref","is-referenced-by-count":3,"title":["Text-Guided HuBERT: Self-Supervised Speech Pre-Training via Generative Adversarial Networks"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5585-6621","authenticated-orcid":false,"given":"Duo","family":"Ma","sequence":"first","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3527-6034","authenticated-orcid":false,"given":"Xianghu","family":"Yue","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer and Engineering, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8979-0835","authenticated-orcid":false,"given":"Junyi","family":"Ao","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1920-5228","authenticated-orcid":false,"given":"Xiaoxue","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer and Engineering, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3191845"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3200915"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref7","first-page":"1","article-title":"Self-supervised learning for speech enhancement","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1868"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022791"},{"key":"ref11","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023187"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054224"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref27","article-title":"g2pe","author":"Park","year":"2019"},{"key":"ref28","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref30","first-page":"10557","article-title":"Flashlight: Enabling innovation in tools for machine learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Kahn","year":"2022"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10380231\/10623285.pdf?arnumber=10623285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T17:41:17Z","timestamp":1724089277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10623285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3438541","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}