{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:40Z","timestamp":1774420180663,"version":"3.50.1"},"reference-count":40,"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889031","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Rhythmic Generative Model for Chinese Cued Speech Gestures Generation"],"prefix":"10.1109","author":[{"given":"Li","family":"Liu","sequence":"first","affiliation":[{"name":"HKUST(GZ),Guangzhou,China"}]},{"given":"Wentao","family":"Lei","sequence":"additional","affiliation":[{"name":"HKUST(GZ),Guangzhou,China"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Guildford,England"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"3","article-title":"Cued speech","volume":"112","author":"Cornett","year":"1967","journal-title":"American Annals of the Deaf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.09.119"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1353\/aad.2019.0031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/deafed\/eni001"},{"key":"ref6","article-title":"An examination of cued speech as a tool for language, literacy, and bilingualism for children who are deaf or hard of hearing","author":"Reynolds","year":"2007","journal-title":"Independent Studies and Capstones. Paper 315."},{"key":"ref7","article-title":"Cued speech: Not just for the deaf anymore","volume-title":"Senior Honors Theses Projects","author":"Baber","year":"2007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095271"},{"key":"ref9","article-title":"A fully convolutional sequence learning approach for cued speech recognition from videos","author":"Katerina","year":"2021","journal-title":"EUSIPCO"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.03.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462090"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2434"},{"key":"ref13","article-title":"Automatic generation of cued speech for the deaf: Status and outlook","author":"Duchnowski","year":"1998","journal-title":"AVSP"},{"key":"ref14","article-title":"Retargeting cued speech hand gestures for different talking heads and speakers","author":"Bailly","year":"2008","journal-title":"AVSP"},{"key":"ref15","article-title":"Diffusion models: A comprehensive survey of methods and applications","author":"Lucas","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"ref17","article-title":"A survey on deep multi-modal learning for body language recognition and generation","author":"Liu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976493"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.10.013"},{"key":"ref20","article-title":"Temporal measures of hand and speech coordination during french cued speech production","volume-title":"International Gesture Workshop","author":"Virginie"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2353"},{"key":"ref22","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","article-title":"A comprehensive survey on human video generation: Challenges, methods, and insights","author":"Lei","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref27","first-page":"135","article-title":"Enriching word vectors with subword information","volume":"5","author":"Piotr","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref28","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.11.004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/700"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3363446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"issue":"12","key":"ref34","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","article-title":"Articulated human detection with flexible mixtures of parts","volume":"35","author":"Yi","year":"2013","journal-title":"TPAMI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976493"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13946"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475223"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"}],"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\/10889031.pdf?arnumber=10889031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:50Z","timestamp":1774416410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889031","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}