{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:25:15Z","timestamp":1776889515551,"version":"3.51.2"},"reference-count":26,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887862","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":3,"title":["SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation"],"prefix":"10.1109","author":[{"given":"Changpeng","family":"Cai","sequence":"first","affiliation":[{"name":"Southeast University,Ping An Technology,Nanjing,China"}]},{"given":"Guinan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,Guangzhou,China"}]},{"given":"Jiao","family":"Li","sequence":"additional","affiliation":[{"name":"Ping An Technology,Nanjing,China"}]},{"given":"Junhao","family":"Su","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China"}]},{"given":"Fei","family":"Shen","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology,Nanjing,China"}]},{"given":"Chenghao","family":"He","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology,Shanghai,China"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Yuanxu","family":"Chen","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Lei","family":"Dai","sequence":"additional","affiliation":[{"name":"Ping An Technology,Nanjing,China"}]},{"given":"Feiyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1913238"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.12987\/9780300280289-018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref9","article-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models","author":"Ma","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094937"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01158-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00703"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"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\/10887862.pdf?arnumber=10887862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:49Z","timestamp":1774416409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887862","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}