{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:10:40Z","timestamp":1776888640334,"version":"3.51.2"},"reference-count":38,"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\/icassp48485.2024.10448079","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11076-11080","source":"Crossref","is-referenced-by-count":13,"title":["SlideSpeech: A Large Scale Slide-Enriched Audio-Visual Corpus"],"prefix":"10.1109","author":[{"given":"Haoxu","family":"Wang","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Shi","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuezhang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab of DAMO Academy,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601981219"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-776"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687895"},{"key":"ref17","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1674"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref21","article-title":"How2: A Large-scale Dataset for Multimodal Language Understanding","volume-title":"Proc. NIPS","author":"Sanabria"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639249"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-678"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-461"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0888-7543(91)90071-L"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478328"},{"key":"ref34","article-title":"KeyBERT: Minimal keyword extraction with BERT","author":"Grootendorst","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-767"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"}],"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\/10448079.pdf?arnumber=10448079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:43:11Z","timestamp":1722580991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448079","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}