{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T12:49:37Z","timestamp":1782737377236,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["No. 2020AAA0108600"],"award-info":[{"award-number":["No. 2020AAA0108600"]}]},{"name":"the State Key Program of the National Natural Science Foundation of China","award":["No.61831022"],"award-info":[{"award-number":["No.61831022"]}]},{"name":"Natural Science Foundation of China","award":["No.62222606 and 62076238"],"award-info":[{"award-number":["No.62222606 and 62076238"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611775","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"6822-6830","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Speech-Driven 3D Face Animation with Composite and Regional Facial Movements"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3036-6930","authenticated-orcid":false,"given":"Haozhe","family":"Wu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5972-3955","authenticated-orcid":false,"given":"Songtao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8449-278X","authenticated-orcid":false,"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University & BNRist, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6801-0510","authenticated-orcid":false,"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8434-2071","authenticated-orcid":false,"given":"Qi","family":"Wen","sequence":"additional","affiliation":[{"name":"ByteDance, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6681-1584","authenticated-orcid":false,"given":"Xiang","family":"Wen","sequence":"additional","affiliation":[{"name":"ByteDance, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548101"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 173--182","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Qiang Cheng, Guoliang Chen, et al. 2016. Deep speech 2: End-to-end speech recognition in english and mandarin. In International conference on machine learning. PMLR, 173--182."},{"key":"e_1_3_2_1_3_1","unstructured":"Alexei Baevski Yuhao Zhou Abdelrahman Mohamed and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. In Advances in Neural Information Processing Systems. 12449--12460."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"e_1_3_2_1_8_1","volume-title":"Facial action coding system. Environmental Psychology & Nonverbal Behavior","author":"Ekman Paul","year":"1978","unstructured":"Paul Ekman and Wallace V Friesen. 1978. Facial action coding system. Environmental Psychology & Nonverbal Behavior (1978)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"e_1_3_2_1_12_1","volume-title":"SPACEx: Speech-driven Portrait Animation with Controllable Expression. arXiv preprint arXiv:2211.09809","author":"Gururani Siddharth","year":"2022","unstructured":"Siddharth Gururani, Arun Mallya, Ting-Chun Wang, Rafael Valle, and Ming-Yu Liu. 2022. SPACEx: Speech-driven Portrait Animation with Controllable Expression. arXiv preprint arXiv:2211.09809 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551574"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_17_1","volume-title":"Audio-driven Facial Animation: A Survey. In IEEE International Conference on Information and Communication Technology Convergence. 614--617","author":"Hwang Jewoong","year":"2022","unstructured":"Jewoong Hwang and Kyoungju Park. 2022. Audio-driven Facial Animation: A Survey. In IEEE International Conference on Information and Communication Technology Convergence. 614--617."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_23_1","volume-title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles. arXiv preprint arXiv:2301.01081","author":"Ma Yifeng","year":"2023","unstructured":"Yifeng Ma, Suzhen Wang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Zhidong Deng, and Xin Yu. 2023. StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles. arXiv preprint arXiv:2301.01081 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.11.001"},{"key":"e_1_3_2_1_25_1","volume-title":"EmoTalk: Speech-driven emotional disentanglement for 3D face animation. arXiv preprint arXiv:2303.11089","author":"Peng Ziqiao","year":"2023","unstructured":"Ziqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, and Zhaoxin Fan. 2023. EmoTalk: Speech-driven emotional disentanglement for 3D face animation. arXiv preprint arXiv:2303.11089 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_2_1_27_1","volume-title":"Vocabulary for performance and quality of service","author":"Recommendation ITUT","year":"2006","unstructured":"ITUT Recommendation. 2006. Vocabulary for performance and quality of service. International Telecommunications Union-Radiocommunication (2006)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"e_1_3_2_1_29_1","volume-title":"Emotion-Controllable Generalized Talking Face Generation. In International Joint Conference on Artificial Intelligence. 1320--1327","author":"Sinha Sanjana","year":"2022","unstructured":"Sanjana Sinha, Sandika Biswas, Ravindra Yadav, and Brojeshwar Bhowmick. 2022. Emotion-Controllable Generalized Talking Face Generation. In International Joint Conference on Artificial Intelligence. 1320--1327."},{"key":"e_1_3_2_1_30_1","volume-title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation. arXiv preprint arXiv:2212.05005","author":"Tang Anni","year":"2022","unstructured":"Anni Tang, Tianyu He, Xu Tan, Jun Ling, Runnan Li, Sheng Zhao, Li Song, and Jiang Bian. 2022. Memories are One-to-Many Mapping Alleviators in Talking Face Generation. arXiv preprint arXiv:2212.05005 (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"ACM SIGGRAPH\/Eurographics Conference on Computer Animation. 275--284","author":"Taylor Sarah L","year":"2012","unstructured":"Sarah L Taylor, Moshe Mahler, Barry-John Theobald, and Iain Matthews. 2012. Dynamic units of visual speech. In ACM SIGGRAPH\/Eurographics Conference on Computer Animation. 275--284."},{"key":"e_1_3_2_1_32_1","volume-title":"Imitator: Personalized Speech-driven 3D Facial Animation. arXiv preprint arXiv:2301.00023","author":"Thambiraja Balamurugan","year":"2022","unstructured":"Balamurugan Thambiraja, Ikhsanul Habibie, Sadegh Aliakbarian, Darren Cosker, Christian Theobalt, and Justus Thies. 2022. Imitator: Personalized Speech-driven 3D Facial Animation. arXiv preprint arXiv:2301.00023 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"e_1_3_2_1_34_1","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research, Vol. 9, 86 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_35_1","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems, Vol. 30 (2017), 5998--6008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"e_1_3_2_1_37_1","volume-title":"Imitating Arbitrary Talking Style for Realistic Audio-Driven Talking Face Synthesis. In ACM International Conference on Multimedia. 1478--1486","author":"Wu Haozhe","year":"2021","unstructured":"Haozhe Wu, Jia Jia, Haoyu Wang, Yishun Dou, Chao Duan, and Qingshan Deng. 2021. Imitating Arbitrary Talking Style for Realistic Audio-Driven Talking Face Synthesis. In ACM International Conference on Multimedia. 1478--1486."},{"key":"e_1_3_2_1_38_1","volume-title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation. arXiv preprint arXiv:2303.09797","author":"Wu Haozhe","year":"2023","unstructured":"Haozhe Wu, Jia Jia, Junliang Xing, Hongwei Xu, Xiangyuan Wang, and Jelo Wang. 2023. MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation. arXiv preprint arXiv:2303.09797 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-498"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Yuyu Xu Andrew W Feng Stacy Marsella and Ari Shapiro. 2013. A practical and configurable lip sync method for games. In Motion on Games. 131--140.","DOI":"10.1145\/2522628.2522904"},{"key":"e_1_3_2_1_42_1","volume-title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis. arXiv preprint arXiv:2301.13430","author":"Ye Zhenhui","year":"2023","unstructured":"Zhenhui Ye, Ziyue Jiang, Yi Ren, Jinglin Liu, Jinzheng He, and Zhou Zhao. 2023. GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis. arXiv preprint arXiv:2301.13430 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Audio-driven talking face video generation with learning-based personalized head pose. arXiv e-prints","author":"Yi Ran","year":"2020","unstructured":"Ran Yi, Zipeng Ye, Juyong Zhang, Hujun Bao, and Yong-Jin Liu. 2020. Audio-driven talking face video generation with learning-based personalized head pose. arXiv e-prints (2020), arXiv-2002."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201292","article-title":"Visemenet: Audio-driven animator-centric speech animation","volume":"37","author":"Zhou Yang","year":"2018","unstructured":"Yang Zhou, Zhan Xu, Chris Landreth, Evangelos Kalogerakis, Subhransu Maji, and Karan Singh. 2018. Visemenet: Audio-driven animator-centric speech animation. ACM Transactions on Graphics, Vol. 37, 4 (2018), 1--10.","journal-title":"ACM Transactions on Graphics"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611775","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:14:33Z","timestamp":1755821673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611775"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":45,"alternative-id":["10.1145\/3581783.3611775","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611775","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}