{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:18Z","timestamp":1775230158392,"version":"3.50.1"},"reference-count":67,"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":[{"DOI":"10.13039\/100016909","name":"Microsoft Research Asia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101523"],"award-info":[{"award-number":["62101523"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hefei Municipal Natural Science Foundation","award":["2022012"],"award-info":[{"award-number":["2022012"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Leading Plan of CAS","award":["XDC08010200"],"award-info":[{"award-number":["XDC08010200"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3275873","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T17:44:40Z","timestamp":1683913480000},"page":"1055-1064","source":"Crossref","is-referenced-by-count":21,"title":["VatLM: Visual-Audio-Text Pre-Training With Unified Masked Prediction for Speech Representation Learning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1196-7781","authenticated-orcid":false,"given":"Qiushi","family":"Zhu","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1919-4943","authenticated-orcid":false,"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-1543","authenticated-orcid":false,"given":"Ziqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China, Hefei, China"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4710-0095","authenticated-orcid":false,"given":"Binxing","family":"Jiao","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1124-0854","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0859-2827","authenticated-orcid":false,"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China, Hefei, China"}]},{"given":"Daxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9748","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2234730"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3115626"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref7","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.","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","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Baevski","year":"2022"},{"key":"ref11","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref14","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref20","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3379877"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.922789"},{"key":"ref28","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref30","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref31","article-title":"A single self-supervised model for many speech modalities enables zero-shot modality transfer","author":"Hsu","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897235"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747760"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref38","article-title":"Opt: Omni-perception pre-trainer for cross-modal understanding and generation","author":"Liu","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26290"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746449"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref50","first-page":"24206","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Akbari","year":"2021"},{"key":"ref51","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref54","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren","year":"2019"},{"key":"ref55","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179001"},{"key":"ref60","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10123989.pdf?arnumber=10123989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:31:12Z","timestamp":1721928672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10123989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3275873","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}