PersonaGest uses a semantic-guided RVQ-VAE with a Semantic-Aware Motion Codebook and contrastive learning in stage one, followed by a Masked Generative Transformer and Style Residual Transformers in stage two, to achieve state-of-the-art co-speech gesture generation with semantic coherence and style
Enabling synergistic full-body control in prompt-based co-speech motion generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
citing papers explorer
-
ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.