{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:12:40Z","timestamp":1772122360365,"version":"3.50.1"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956600","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"491-498","source":"Crossref","is-referenced-by-count":8,"title":["Learning Speaker-specific Lip-to-Speech Generation"],"prefix":"10.1109","author":[{"given":"Munender","family":"Varshney","sequence":"first","affiliation":[{"name":"Indian institute of Technology,Computer Science and Engineering department,Kanpur,India"}]},{"given":"Ravindra","family":"Yadav","sequence":"additional","affiliation":[{"name":"Indian institute of Technology,Electrical department,Kanpur,India"}]},{"given":"Vinay P.","family":"Namboodiri","sequence":"additional","affiliation":[{"name":"University of Bath,UK"}]},{"given":"Rajesh M","family":"Hegde","sequence":"additional","affiliation":[{"name":"Indian institute of Technology,Electrical department,Kanpur,India"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref38","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-293"},{"key":"ref32","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref30","article-title":"Adversarial-metric learning for audio-visual cross-modal matching","author":"zheng","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with lstms for lipreading","author":"stafylakis","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.69"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2010.5709752"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2509"},{"key":"ref61","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref28","article-title":"Transformer-based conditional variational autoencoder for controllable story generation","author":"fang","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054554"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1090"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"jacob","year":"2019","journal-title":"NAACL"},{"key":"ref24","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414040"},{"key":"ref59","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00817"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref55","article-title":"Variational transformers for diverse response generation","author":"lin","year":"2020"},{"key":"ref54","article-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00221"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00037"},{"key":"ref11","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-021-01863-z"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093378"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747559"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1114783109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-140-5-200403020-00011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5_39"},{"key":"ref6","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1995.03520270061032"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref7","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"assael","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093565"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1823"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682868"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012588"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956600.pdf?arnumber=9956600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:05:53Z","timestamp":1671462353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956600","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}