{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:21:50Z","timestamp":1776529310554,"version":"3.51.2"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414053","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6658-6662","source":"Crossref","is-referenced-by-count":11,"title":["Vset: A Multimodal Transformer for Visual Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Karthik","family":"Ramesh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wupeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.381436"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.396976"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1250\/ast.16.311"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref15","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref16","article-title":"Transformer with gaussian weighted self-attention for speech enhancement","author":"kim","year":"2019","journal-title":"arXiv preprint arXiv 1910 01500"},{"key":"ref17","article-title":"Boosting objective scores of speech enhancement model through metricgan post-processing","author":"fu","year":"2020","journal-title":"arXiv preprint arXiv 2006 10226"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1003743","article-title":"No, there is no 150 ms lead of visual speech on auditory speech, but a range of audiovisual asynchronies varying from small audio lead to large audio lag","volume":"10","author":"schwartz","year":"2014","journal-title":"PLoS Comput Biol"},{"key":"ref19","article-title":"Nezha: Neural contextualized representation for chinese language understanding","author":"wei","year":"2019","journal-title":"arXiv preprint arXiv 1909 01771"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3675-12.2013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.283.5406.1272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref5","article-title":"Visual speech enhancement","author":"gabbay","year":"2017","journal-title":"arXiv preprint arXiv 1711 07064"},{"key":"ref8","article-title":"Cochleanet: A robust language-independent audio-visual model for speech enhancement","author":"gogate","year":"2019","journal-title":"arXiv preprint arXiv 1909 10407"},{"key":"ref7","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018","journal-title":"arXiv preprint arXiv 1804 03583"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414053.pdf?arnumber=9414053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:08Z","timestamp":1652197268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414053","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}