{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T01:50:07Z","timestamp":1783389007951,"version":"3.54.6"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012656","name":"Shanghai Key Laboratory of Digital Media Processing and Transmission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012656","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687925","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["SingAvatar: High-fidelity Audio-driven Singing Avatar Synthesis"],"prefix":"10.1109","author":[{"given":"Wentao","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anni","family":"Tang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Ling","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiheng","family":"Liao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref4","article-title":"Generative adversarial nets","volume-title":"NeurIPS","volume":"27","author":"Goodfellow"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3410700.3425435"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3409380\/mm2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00366"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref18","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687925.pdf?arnumber=10687925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:38:41Z","timestamp":1727764721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687925","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}