{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/echomask-speech-queried-attention-based-mask","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","arxiv_id":"2504.09209","date":"2025-04-12","proceeding":null,"authors":["Xiangyue Zhang","Jianfang Li","Jiaxu Zhang","Jianqiang Ren","Liefeng Bo","Zhigang Tu"],"abstract":"Masked modeling framework has shown promise in co-speech motion generation. However, it struggles to identify semantically significant frames for effective motion masking. In this work, we propose a speech-queried attention-based mask modeling framework for co-speech motion generation. Our key insight is to leverage motion-aligned speech features to guide the masked motion modeling process, selectively masking rhythm-related and semantically expressive motion frames. Specifically, we first propose a motion-audio alignment module (MAM) to construct a latent motion-audio joint space. In this space, both low-level and high-level speech features are projected, enabling motion-aligned speech representation using learnable speech queries. Then, a speech-queried attention mechanism (SQA) is introduced to compute frame-level attention scores through interactions between motion keys and speech queries, guiding selective masking toward motion frames with high attention scores. Finally, the motion-aligned speech features are also injected into the generation network to facilitate co-speech motion generation. Qualitative and quantitative evaluations confirm that our method outperforms existing state-of-the-art approaches, successfully producing high-quality co-speech motion.","url_abs":"https://arxiv.org/abs/2504.09209v2","url_pdf":"https://arxiv.org/pdf/2504.09209v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"gesture-generation","task_name":"Gesture Generation"},{"task_slug":"motion-generation","task_name":"Motion Generation"},{"task_slug":"rhythm","task_name":"Rhythm"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gesture-generation-on-beat2","task":"Gesture Generation","dataset":"BEAT2","model":"EchoMask","rank_in_archive_order":5,"of":14,"metrics":{"FGD":"0.4623"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.09209","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}