{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:53:03Z","timestamp":1781761983995,"version":"3.54.5"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"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":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11557042","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation"],"prefix":"10.1109","author":[{"given":"Federico","family":"Nocentini","sequence":"first","affiliation":[{"name":"University of Florence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwanggyoon","family":"Seo","sequence":"additional","affiliation":[{"name":"Flawless AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingju","family":"Liu","sequence":"additional","affiliation":[{"name":"Flawless AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Ferrari","sequence":"additional","affiliation":[{"name":"University of Florence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Berretti","sequence":"additional","affiliation":[{"name":"University of Florence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Ferman","sequence":"additional","affiliation":[{"name":"Flawless AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeongwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Garrido","sequence":"additional","affiliation":[{"name":"Flawless AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akin","family":"Caliskan","sequence":"additional","affiliation":[{"name":"Flawless AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-938"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICMI.2002.1167047"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref7","article-title":"Emotional speech-driven animation with content-emotion disentanglement","author":"Dan\u02c7\u02c7ek","year":"2023","journal-title":"arXiv preprint arXiv:2306.08990"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053366"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_20"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614157"},{"key":"ref14","volume-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref17","volume-title":"Vowels and consonants. Manchu Grammar","author":"Ladefoged","year":"2000"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00347"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511843891.014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02726-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_2"},{"key":"ref22","volume-title":"Freetalk: Emotional topology-free 3d talking heads","author":"Nocentini","year":"2026"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43148-7_29"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00283"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref28","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1794"},{"key":"ref34","article-title":"3diface: Diffusion-based speech-driven 3d facial animation and editing","author":"Thambiraja","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1274940.1274947"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3677388.3696320"},{"key":"ref38","article-title":"Multiface: A dataset for neural face rendering","author":"Wuu","year":"2022","journal-title":"arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2522628.2522904"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_14"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687618"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11557042.pdf?arnumber=11557042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:06:43Z","timestamp":1781759203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11557042","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}