{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T17:05:02Z","timestamp":1778087102778,"version":"3.51.4"},"reference-count":37,"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\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","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\/icassp48485.2024.10447284","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4325-4329","source":"Crossref","is-referenced-by-count":10,"title":["Exploring Phonetic Context-Aware Lip-Sync for Talking Face Generation"],"prefix":"10.1109","author":[{"given":"Se Jin","family":"Park","sequence":"first","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab. School of EE,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab. School of EE,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongsoo","family":"Choi","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab. School of EE,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab. School of EE,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415207"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168283"},{"key":"ref3","article-title":"Phoneme recognizer based on long temporal context","volume-title":"Speech Processing Group, Faculty of Information Technology","author":"Schwarz","year":"2006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2011.12.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987720"},{"key":"ref6","article-title":"Audio-visual synchronisation in the wild","author":"Chen","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10861"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref19","article-title":"Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref24","first-page":"642","article-title":"Unilmv2: Pseudo-masked language models for unified language model pre-training","volume-title":"International conference on machine learning","author":"Bao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref26","first-page":"2758","article-title":"Lip to speech synthesis with visual context attentional gan","volume":"34","author":"Kim","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11311"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00520"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"}],"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\/10447284.pdf?arnumber=10447284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:29:53Z","timestamp":1722572993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447284","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}