{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:05:53Z","timestamp":1765357553695,"version":"3.41.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447978","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7945-7949","source":"Crossref","is-referenced-by-count":18,"title":["FreeTalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness"],"prefix":"10.1109","author":[{"given":"Sicheng","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Zunnan","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Haiwei","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]},{"given":"Yongkang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Northwest A&F University"}]},{"given":"Shaoli","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Mingming","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Melbourne"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095203"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28458"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3330935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14734"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414\/mm2"},{"article-title":"Human motion diffusion as a generative prior","year":"2023","author":"Shafir","key":"ref13"},{"article-title":"Pretrained diffusion models for unified human motion synthesis","year":"2022","author":"Ma","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392462"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612503"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Classifier-free diffusion guidance","year":"2022","author":"Ho","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616114"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329472"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"article-title":"Reformer: The efficient transformer","volume-title":"International Conference on Learning Representations","author":"Kitaev","key":"ref33"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447978.pdf?arnumber=10447978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:03:53Z","timestamp":1748365433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447978","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}