{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T12:01:02Z","timestamp":1790856062485,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763998","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Echo: Enhancing Conversational Behavior Generation via Hierarchical Semantic Comprehension with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7318-9682","authenticated-orcid":false,"given":"Haiwei","family":"Xue","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8530-485X","authenticated-orcid":false,"given":"Yanbo","family":"Fan","sequence":"additional","affiliation":[{"name":"Nanjing University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5813-3875","authenticated-orcid":false,"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8533-0524","authenticated-orcid":false,"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDPVT.2004.1335299"},{"key":"e_1_3_3_2_3_1","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Chuyuan Fu Keerthana Gopalakrishnan Karol Hausman et\u00a0al. 2022. Do As I Can Not As I Say: Grounding Language in Robotic Affordances."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Simon Alexanderson Rajmund Nagy Jonas Beskow and Gustav\u00a0Eje Henter. 2023. Listen denoise action! audio-driven motion synthesis with diffusion models. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201320.","DOI":"10.1145\/3592458"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Tenglong Ao Qingzhe Gao Yuke Lou Baoquan Chen and Libin Liu. 2022. Rhythmic gesticulator: Rhythm-aware co-speech gesture synthesis with hierarchical neural embeddings. ACM Transactions on Graphics (TOG) 41 6 (2022) 1\u201319.","DOI":"10.1145\/3550454.3555435"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Tenglong Ao Zeyi Zhang and Libin Liu. 2023. Gesturediffuclip: Gesture diffusion model with clip latents. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201318.","DOI":"10.1145\/3592097"},{"key":"e_1_3_3_2_7_1","unstructured":"Yuxuan Bian Ailing Zeng Xuan Ju Xian Liu Zhaoyang Zhang Wei Liu and Qiang Xu. 2024. Adding Multi-modal Controls to Whole-body Human Motion Generation."},{"key":"e_1_3_3_2_8_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687677"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616117"},{"key":"e_1_3_3_2_12_1","unstructured":"J. Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0013570"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680625"},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"E. Ghaleb B. Khaertdinov W. Pouw M. Rasenberg J. Holler A. \u00d6zy\u00fcrek and R. Fern\u00e1ndez. 2024. Learning Co-Speech Gesture Representations in Dialogue through Contrastive Learning: An Intrinsic Evaluation.","DOI":"10.1145\/3678957.3685707"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"T. Guichoux L. Soulier N. Obin and C. Pelachaud. 2024. 2D or not 2D: How Does the Dimensionality of Gesture Representation Affect 3D Co-Speech Gesture Generation?","DOI":"10.1145\/3652988.3673934"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614158"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"crossref","unstructured":"A.\u00a0B. Hostetter. 2011. When do gestures communicate? A meta-analysis. Psychological bulletin 137 2 (2011) 389\u2013416.","DOI":"10.1037\/a0022128"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807572"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329472"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616120"},{"key":"e_1_3_3_2_23_1","first-page":"1047","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Lee G.","year":"2019","unstructured":"G. Lee, Z. Deng, S. Ma, T. Shiratori, S.\u00a0S. Srinivasa, and Y. Sheikh. 2019. Talking with hands 16.2 m: A large-scale dataset of synchronized body-finger motion and audio for conversational motion analysis and synthesis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. IEEE, Seoul, South Korea, 1047\u20131056."},{"key":"e_1_3_3_2_24_1","unstructured":"Ziyang Ma Zhisheng Zheng Jiaxin Ye Jinchao Li Zhifu Gao Shiliang Zhang and Xie Chen. 2024. emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation. Findings of the Association for Computational Linguistics: ACL 2024 1 1 (2024) 1. Findings of ACL 2024."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Shivam Mehta Siyang Wang Simon Alexanderson Jonas Beskow \u00c9va Sz\u00e9kely and Gustav\u00a0Eje Henter. 2023. Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis.","DOI":"10.21437\/SSW.2023-24"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00138"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00101"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Simbarashe Nyatsanga Taras Kucherenko Chaitanya Ahuja Gustav\u00a0Eje Henter and Michael Neff. 2023. A Comprehensive Review of Data-Driven Co-Speech Gesture Generation. Computer Graphics Forum 42 2 (2023) 569\u2013596.","DOI":"10.1111\/cgf.14776"},{"key":"e_1_3_3_2_29_1","volume-title":"GPT-4 technical report","year":"2023","unstructured":"OpenAI. 2023. GPT-4 technical report. Technical Report. OpenAI."},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667023"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"crossref","unstructured":"Kalakonda\u00a0Sai Shashank Shubh Maheshwari and Ravi\u00a0Kiran Sarvadevabhatla. 2024. MoRAG\u2013Multi-Fusion Retrieval Augmented Generation for Human Motion.","DOI":"10.1109\/WACV61041.2025.00448"},{"key":"e_1_3_3_2_32_1","volume-title":"A conversational model of multimodal interaction","author":"Stein Adelheit","year":"1993","unstructured":"Adelheit Stein and Ulrich Thiel. 1993. A conversational model of multimodal interaction. Citeseer, University Park, PA, USA."},{"key":"e_1_3_3_2_33_1","unstructured":"Parisa\u00a0Ghanad Torshizi Laura\u00a0B Hensel Ari Shapiro and Stacy\u00a0C Marsella. 2025. Large Language Models for Virtual Human Gesture Selection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.14408 (2025)."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203360859"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Petra Wagner Zofia Malisz and Stefan Kopp. 2014. Gesture and speech in interaction: An overview. 209\u2013232\u00a0pages.","DOI":"10.1016\/j.specom.2013.09.008"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"e_1_3_3_2_38_1","first-page":"24824","volume-title":"Advances in Neural Information Processing Systems","author":"Wei J.","year":"2022","unstructured":"J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q.\u00a0V. Le, and D. Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems. Curran Associates, Inc., New Orleans, LA, USA, 24824\u201324837."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15167"},{"key":"e_1_3_3_2_40_1","unstructured":"Haiwei Xue Xiangyang Luo Zhanghao Hu Xin Zhang Xunzhi Xiang Yuqin Dai Jianzhuang Liu Zhensong Zhang Minglei Li Jian Yang et\u00a0al. 2024a. Human motion video generation: A survey. Authorea Preprints 1 1 (2024) 1\u201321."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448208"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616114"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"crossref","unstructured":"Youngwoo Yoon Bok Cha Joo-Haeng Lee Minsu Jang Jaeyeon Lee Jaehong Kim and Geehyuk Lee. 2020. Speech gesture generation from the trimodal context of text audio and speaker identity. ACM Transactions on Graphics 39 6 (2020) 222:1\u2013222:16.","DOI":"10.1145\/3414685.3417838"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558058"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"crossref","unstructured":"Xin Zeng Xiaoyu Wang Tengxiang Zhang Chun Yu Shengdong Zhao and Yiqiang Chen. 2024. GestureGPT: Toward zero-shot free-form hand gesture understanding with large language model agents. Proceedings of the ACM on Human-Computer Interaction 8 ISS (2024) 462\u2013499.","DOI":"10.1145\/3698145"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Zeyi Zhang Tenglong Ao Yuyao Zhang Qingzhe Gao Chuan Lin Baoquan Chen and Libin Liu. 2024. Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201317.","DOI":"10.1145\/3658134"},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:32:58Z","timestamp":1765251178000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":46,"alternative-id":["10.1145\/3757377.3763998","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763998","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}