SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
Paper • 2412.16563 • Published
Co-Speech Gesture Generation by Xiangyue Zhang
Official SemTalk, EchoMask, GlobalDiff, and StreamTalk papers, models, and data for co-speech gesture generation.
-
-
X-Zhang/SemTalk
Updated -
X-Zhang/SemTalk-Inference-Data
Updated • 77 -
EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation
Paper • 2504.09209 • Published -
X-Zhang/EchoMask
Updated • 1 -
X-Zhang/EchoMask-Inference-Data
Updated • 57 -
Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints
Paper • 2511.10076 • Published -
X-Zhang/GlobalDiff
Updated -
X-Zhang/GlobalDiff-Inference-Data
Updated • 28 -
StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
Paper • 2608.01643 • Published -
X-Zhang/StreamTalk
Updated • 1 -
X-Zhang/StreamTalk-Inference-Data
Updated • 140