Reliable co speech gesture generation balancing semantics and rhythm

When Semantics Matter: Reliability-Aware Semantic-Rhythm Control for Co-Speech Gesture Generation

Computer Vision and Pattern Recognition

Summary

Making animated gestures that match spoken words can be tricky because gestures should flow with the speech rhythm and also show the meaning behind the words. The authors found that past methods rely too much on sound patterns and not enough on the actual meaning of speech, which can cause gestures to miss important content. They designed a new system that watches how much meaning influences motion and adjusts the gestures accordingly, improving how well gestures match both meaning and rhythm. Their system also handles noisy sound better, so it works well even in less-than-ideal listening situations.

What this means in practice

  • For virtual avatar developers: Create avatars that produce gestures well matched to both speech rhythm and meaning, even in noisy environments.$Commercial implications: Enables development of more natural and reliable virtual assistants and game characters for customer-facing applications.
  • For augmented reality interface designers: Integrate more expressive and rhythmically synchronized gestures into AR systems that respond to spoken commands under real-world noise.

Authors

Zhirui Xing, Long Ye, Kaige Li, Ziyi Xu, Ming Meng

Abstract

Co-speech gesture generation aims to synthesize natural gestures that are both temporally synchronized with speech and semantically consistent with the spoken content. Although recent methods can generate rhythmically plausible motions, they often rely heavily on acoustic prosody while underutilizing textual semantics, especially when semantic annotations are incomplete, noisy, or unavailable. Consequently, the generated gestures may follow speech rhythm while failing to express the intended semantics. To address this problem, we propose a reliability-aware semantic-rhythm control framework for co-speech gesture generation. We first learn a discrete motion prior that represents continuous gestures in a compact and structured motion-code space. We then introduce a dual-branch semantic contribution estimation mechanism consisting of a full multimodal branch and an audio-only branch. Their distributional discrepancy is formulated as conditional information gain to quantify how much textual semantics changes the predicted motion. Based on this estimate, a controllable semantic-rhythm objective selectively strengthens semantic guidance in content-relevant segments while limiting unnecessary semantic intervention in rhythm-dominant segments. Furthermore, we treat background noise as an acoustic reliability condition and introduce noise-conditioned feature modulation together with beneficial latent perturbation to improve generation robustness under realistic acoustic environments. Experiments on benchmark datasets demonstrate that the proposed framework achieves a favorable balance among semantic expressiveness, rhythmic synchronization, motion diversity, and robustness, enabling reliable and controllable co-speech gesture generation.