{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:35:15Z","timestamp":1776116115926,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317357","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1492-1499","source":"Crossref","is-referenced-by-count":3,"title":["RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations"],"prefix":"10.1109","author":[{"given":"Neha","family":"Sahipjohn","sequence":"first","affiliation":[{"name":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neil","family":"Shah","sequence":"additional","affiliation":[{"name":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishal","family":"Tambrahalli","sequence":"additional","affiliation":[{"name":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vineet","family":"Gandhi","sequence":"additional","affiliation":[{"name":"CVIT, Kohli Centre for Intelligent Systems, IIIT Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12131"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00037"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1044\/2021_AJA-21-00112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-194"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548194"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747427"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3162495"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10770"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3191677"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096464"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19966"},{"key":"ref26","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956600"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3126925"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01802"},{"key":"ref32","volume-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref34","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref39","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref42","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"OpenAI Blog"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.4324\/9780203098752"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,10,31]]},"end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317357.pdf?arnumber=10317357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:53:59Z","timestamp":1709405639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317357","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}