{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:23:26Z","timestamp":1784132606064,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889163","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Hao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongliang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojie","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Xie","sequence":"additional","affiliation":[{"name":"National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Wu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erwei","family":"Yin","sequence":"additional","affiliation":[{"name":"National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SCSP.2017.7973348"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.09.119"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237849"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref6","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. of ICLR","author":"Simonyan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202842"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref12","first-page":"18806","article-title":"Synthvsr: Scaling up visual speech recognition with synthetic supervision","volume-title":"Proc. of CVPR","author":"Liu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054384"},{"key":"ref14","first-page":"1","article-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animation","author":"Wei","year":"2024","journal-title":"arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185894"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446336"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref23","first-page":"1","article-title":"Learn an effective lip reading model without pains","author":"Feng","year":"2020","journal-title":"arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref27","first-page":"1","article-title":"Lip reading in profile","volume-title":"Proc. of BMVC","author":"Chung"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414659"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446453"},{"key":"ref32","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. of ICLR","author":"Kingma"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889163.pdf?arnumber=10889163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:25Z","timestamp":1774416145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889163","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}