Papers › EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation

EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation

12 Apr 2025arXiv:2504.09209archive 2025-07-28

Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Jianqiang Ren, Liefeng Bo, Zhigang Tu

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Gesture GenerationMotion GenerationRhythm

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Gesture Generation BEAT2 EchoMask FGD 0.4623 #5 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections