{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:15:48Z","timestamp":1768072548376,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023284","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"465-471","source":"Crossref","is-referenced-by-count":16,"title":["AVSE Challenge: Audio-Visual Speech Enhancement Challenge"],"prefix":"10.1109","author":[{"given":"Andrea Lorena Aldana","family":"Blanco","sequence":"first","affiliation":[{"name":"University of Edinburgh,Edinburgh,UK"}]},{"given":"Cassia","family":"Valentini-Botinhao","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Edinburgh,UK"}]},{"given":"Ondrej","family":"Klejch","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Edinburgh,UK"}]},{"given":"Mandar","family":"Gogate","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,Edinburgh,UK"}]},{"given":"Kia","family":"Dashtipour","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,Edinburgh,UK"}]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,Edinburgh,UK"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Edinburgh,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-019-09645-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.04.017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref7","article-title":"The conver-sation: Deep audio-visual speech enhancement","volume":"abs\/1804.04121","author":"Afouras","year":"2018","journal-title":"CoRR"},{"key":"ref8","article-title":"A ro-bust audio-visual speech enhancement model","volume-title":"Proc. ICASSP","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.1998-350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1574"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415105"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.01.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1641"},{"key":"ref15","volume-title":"AV Speech Enhancement Challenge using a Real Noisy Corpus","author":"Gogate"},{"key":"ref16","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref20","article-title":"Per-ceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone net-works and codecs","volume-title":"Proc. ICASSP","author":"Rix"},{"key":"ref21","article-title":"Efficient intelligibility evaluation using key-word spotting: a study on audio-visual speech enhancement","author":"Blanco","year":"2022","journal-title":"submission"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"U-Net: Con-volutional Networks for Biomedical Image Segmentation","volume-title":"Proc. MICCAI","author":"Ronneberger"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2537"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023284.pdf?arnumber=10023284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:09:07Z","timestamp":1707811747000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023284","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}