MIBURI: Towards Expressive Interactive Gesture Synthesis

TL;DR

MIBURI is a novel online framework that generates expressive, synchronized full-body gestures and facial expressions for ECAs in real-time, using hierarchical motion encoding and causal autoregressive modeling.

Contribution

It introduces the first real-time, causal system for expressive gesture synthesis conditioned on speech, combining hierarchical motion encoding with LLM-based context understanding.

Findings

Produces natural, contextually aligned gestures in real-time.

Outperforms recent baselines in naturalness and expressiveness.

Enables expressive gestures without long run-time dependencies.

Abstract

Embodied Conversational Agents (ECAs) aim to emulate human face-to-face interaction through speech, gestures, and facial expressions. Current large language model (LLM)-based conversational agents lack embodiment and the expressive gestures essential for natural interaction. Existing solutions for ECAs often produce rigid, low-diversity motions, that are unsuitable for human-like interaction. Alternatively, generative methods for co-speech gesture synthesis yield natural body gestures but depend on future speech context and require long run-times. To bridge this gap, we present MIBURI, the first online, causal framework for generating expressive full-body gestures and facial expressions synchronized with real-time spoken dialogue. We employ body-part aware gesture codecs that encode hierarchical motion details into multi-level discrete tokens. These tokens are then autoregressively generated by a two-dimensional causal framework conditioned on LLM-based speech-text embeddings, modeling both temporal dynamics and part-level motion hierarchy in real time. Further, we introduce auxiliary objectives to encourage expressive and diverse gestures while preventing convergence to static poses. Comparative evaluations demonstrate that our causal and real-time approach produces natural and contextually aligned gestures against recent baselines. We urge the reader to explore demo videos on https://vcai.mpi-inf.mpg.de/projects/MIBURI/.