BROWSE
Detail
Conference Paper
SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents
Cited 17 time in 
Share 
Share
- Authors
- Youngwoo Yoon, Keunwoo Park, Minsu Jang, Jaehong Kim, Geehyuk Lee
- Issue Date
- 2021-10
- Citation
- ACM Symposium on User Interface Software and Technology (UIST) 2021, pp.826-840
- Publisher
- ACM
- Language
- English
- Type
- Conference Paper
- Abstract
- Non-verbal behavior is essential for embodied agents like social robots, virtual avatars, and digital humans. Existing behavior authoring approaches including keyframe animation and motion capture are too expensive to use when there are numerous utterances requiring gestures. Automatic generation methods show promising results, but their output quality is not satisfactory yet, and it is hard to modify outputs as a gesture designer wants. We introduce a new gesture generation toolkit, named SGToolkit, which gives a higher quality output than automatic methods and is more efficient than manual authoring. For the toolkit, we propose a neural generative model that synthesizes gestures from speech and accommodates fine-level pose controls and coarse-level style controls from users. The user study with 24 participants showed that the toolkit is favorable over manual authoring, and the generated gestures were also human-like and appropriate to input speech. The SGToolkit is platform agnostic, and the code is available at https://github.com/ai4r/SGToolkit.
- KSP Keywords
- Automatic generation, Behavior authoring, Embodied conversational agents, Generative models, Gesture authoring, Gesture generation, Human-like, Motion capture, Non-verbal behavior, Output quality, Quality output