{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:26:36Z","timestamp":1776889596128,"version":"3.51.2"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446297","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12001-12005","source":"Crossref","is-referenced-by-count":7,"title":["Audiovisual Speaker Separation with Full- and Sub-Band Modeling in the Time-Frequency Domain"],"prefix":"10.1109","author":[{"given":"Vahid Ahmadi","family":"Kalkhorani","sequence":"first","affiliation":[{"name":"Ohio State University,Department of Computer Science and Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Tan","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buye","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta Reality Labs,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Ohio State University,Department of Computer Science and Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2096212"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2261814"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-183"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref6","article-title":"Visual speech enhancement using noise-invariant training","author":"Gabbay","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2671"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1697"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_18"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00139"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2853566"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2516"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1617"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/math11122665"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref20","first-page":"638","article-title":"Attentive fusion enhanced audio-visual encoding for transformer based robust speech recognition","volume-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Wei"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2098"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref28","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"}],"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\/10446297.pdf?arnumber=10446297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:09:31Z","timestamp":1722575371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446297","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}