{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:17:38Z","timestamp":1784301458497,"version":"3.55.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887628","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Diffusion-based Unsupervised Audio-visual Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Jean-Eudes","family":"Ayilo","sequence":"first","affiliation":[{"name":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mostafa","family":"Sadeghi","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romain","family":"Serizel","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[{"name":"Université Grenoble Alpes,Inria,Grenoble,France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023284"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1400"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153265"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.30420\/456164054"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-701"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3207349"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094849"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446610"},{"key":"ref17","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr\u00e0","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096064"},{"key":"ref20","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-232"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3449221"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632676"},{"key":"ref24","article-title":"Algorithms for non-negative matrix factorization","volume":"13","author":"Lee","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447736"},{"key":"ref26","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref28","article-title":"Understanding diffusion objectives as the elbo with simple data augmentation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Kingma"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm11181"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref32","article-title":"Lipvoicer: Generating speech from silent videos guided by lip reading","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yemini"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref34","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"ArXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-860"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193049"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446625"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887628.pdf?arnumber=10887628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:13Z","timestamp":1774416133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887628","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}