{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:40:05Z","timestamp":1782834005542,"version":"3.54.5"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094724","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Real-Time Audio-Visual End-To-End Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Zirun","family":"Zhu","sequence":"first","affiliation":[{"name":"Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemin","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Tang","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sefik Emre","family":"Eskimez","sequence":"additional","affiliation":[{"name":"Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaming","family":"Wang","sequence":"additional","affiliation":[{"name":"Redmond,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10041"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00359"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10962"},{"key":"ref17","author":"yang","year":"2022","journal-title":"i-code An integrative and composable multimodal learning framework"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054528"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","author":"afouras","year":"2018","journal-title":"LRS3- TED A large-scale dataset for visual speech recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref27","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2730"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref4","first-page":"2728","article-title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","author":"wang","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10229"},{"key":"ref5","first-page":"3481","article-title":"Face-Filter: Audio-Visual Speech Separation Using Still Images","author":"chung","year":"2020","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094724.pdf?arnumber=10094724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:49Z","timestamp":1700506969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094724","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}