{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:12:49Z","timestamp":1775913169907,"version":"3.50.1"},"reference-count":28,"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\/icassp48485.2024.10446625","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10806-10810","source":"Crossref","is-referenced-by-count":9,"title":["AV2WAV: Diffusion-Based Re-Synthesis from Continuous Self-Supervised Features for Audio-Visual Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Ju-Chieh","family":"Chou","sequence":"first","affiliation":[{"name":"Toyota Technological Institute,Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Ming","family":"Chien","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute,Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute,Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref10","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref11","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2021","journal-title":"ICLR"},{"key":"ref12","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"ICLR","author":"Chen"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref16","article-title":"Audio-visual speech enhancement with score-based generative models","author":"Richter","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref19","article-title":"SDR\u2013half-baked or well done?","author":"Le Roux","year":"2019","journal-title":"ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref21","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023284"},{"key":"ref23","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref25","article-title":"CSTR VCTK corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"},{"key":"ref27","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr\u00e0","year":"2022"},{"key":"ref28","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"ICLR"}],"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\/10446625.pdf?arnumber=10446625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:23:01Z","timestamp":1722576181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446625","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}