{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:13:56Z","timestamp":1784301236326,"version":"3.55.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018AAA0102504"],"award-info":[{"award-number":["2018AAA0102504"]}]},{"name":"National Key R&D Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2021GY-025"],"award-info":[{"award-number":["2021GY-025"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2021GXLH-Z-097"],"award-info":[{"award-number":["2021GXLH-Z-097"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3214100","type":"journal-article","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T19:40:36Z","timestamp":1665603636000},"page":"6717-6728","source":"Crossref","is-referenced-by-count":20,"title":["AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Persons"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1826-7419","authenticated-orcid":false,"given":"Xinsheng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qicong","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-8781","authenticated-orcid":false,"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0693-8852","authenticated-orcid":false,"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[{"name":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747380"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref15","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/141"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref17","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref19","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref18","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref51","first-page":"37","article-title":"End-to-end speech-driven facial animation with temporal GANs","author":"vougioukas","year":"2019","journal-title":"CVPR Workshops"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683872"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref42","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref49","article-title":"You said that?","author":"chung","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref7","first-page":"3473","article-title":"Text-driven speech animation with emotion control","volume":"14","author":"chae","year":"2020","journal-title":"KSII Trans Internet Inf Syst"},{"key":"ref9","article-title":"From inference to generation: End-to-end fully self-supervised generation of human face from speech","author":"choi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_71"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21785\/icad2019.032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2944-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917336"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887027"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref31","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820818"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref77","article-title":"Synthesizing naturalistic and meaningful speech-driven behaviors","author":"nourabadi","year":"2017"},{"key":"ref32","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref76","first-page":"7137","article-title":"First order motion model for image animation","volume":"32","author":"siarohin","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","article-title":"ObamaNet: Photo-realistic lip-sync from text","author":"kumar","year":"2017"},{"key":"ref1","article-title":"What comprises a good talking-head video generation?: A survey and benchmark","author":"chen","year":"2020"},{"key":"ref39","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"yi","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref71","first-page":"3","article-title":"Rectifier Nonlinearities Improve Neural Network Acoustic Models","volume":"30","author":"maas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref70","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00923"},{"key":"ref24","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref25","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1006"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2357"},{"key":"ref22","first-page":"17022","article-title":"Hifi-Gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref21","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2016394"},{"key":"ref27","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09917325.pdf?arnumber=9917325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:16:59Z","timestamp":1702325819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9917325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3214100","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}