{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:06:17Z","timestamp":1761897977086,"version":"3.37.3"},"reference-count":21,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp48485.2024.10446142","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10926-10930","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Modality Speech Recognition Driven by Background Visual Scenes"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Luo","sequence":"first","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhoujian","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000436"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1101-19.2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.283.5406.1272"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5580-0_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3163771"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093314"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/2331216519881346"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.04.008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainres.2008.03.071"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119182"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref16"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","year":"2022","author":"Shi","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446142.pdf?arnumber=10446142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:04:34Z","timestamp":1722575074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446142","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}