{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:49:48Z","timestamp":1770230988200,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301075\/62171250"],"award-info":[{"award-number":["62301075\/62171250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800480","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"426-430","source":"Crossref","is-referenced-by-count":2,"title":["Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective"],"prefix":"10.1109","author":[{"given":"Chen","family":"Chen","sequence":"first","affiliation":[{"name":"BNRist, Tsinghua University,Center for Speech and Language Technologies"}]},{"given":"Xiaolou","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}]},{"given":"Zehua","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}]},{"given":"Lantian","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University,Center for Speech and Language Technologies"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"Assael","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10770"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746401"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref7","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref14","volume-title":"A review on multivariate mutual information","author":"Srinivasa","year":"2006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2012.6358906"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-013-0458-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102422"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446545"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447758"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257839"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2509"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095796"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800480.pdf?arnumber=10800480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:37:38Z","timestamp":1736883458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800480","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}