English

Incorporating Spatial Awareness in Data-Driven Gesture Generation for Virtual Agents

Human-Computer Interaction 2024-08-09 v1 Computation and Language Graphics

Abstract

This paper focuses on enhancing human-agent communication by integrating spatial context into virtual agents' non-verbal behaviors, specifically gestures. Recent advances in co-speech gesture generation have primarily utilized data-driven methods, which create natural motion but limit the scope of gestures to those performed in a void. Our work aims to extend these methods by enabling generative models to incorporate scene information into speech-driven gesture synthesis. We introduce a novel synthetic gesture dataset tailored for this purpose. This development represents a critical step toward creating embodied conversational agents that interact more naturally with their environment and users.

Keywords

Cite

@article{arxiv.2408.04127,
  title  = {Incorporating Spatial Awareness in Data-Driven Gesture Generation for Virtual Agents},
  author = {Anna Deichler and Simon Alexanderson and Jonas Beskow},
  journal= {arXiv preprint arXiv:2408.04127},
  year   = {2024}
}
R2 v1 2026-06-28T18:07:09.381Z