상세정보
학술대회
A Large, Crowdsourced Evaluation of Gesture Generation Systems on Common Data: The GENEA Challenge 2020
- 저자
- Taras Kucherenko, Patrik Jonell, 윤영우, Pieter Wolfert, Gustav Eje Henter
- 발행일
- 202104
- 출처
- International Conference on Intelligent User Interfaces (IUI) 2021, pp.11-21
- 초록
- Co-speech gestures, gestures that accompany speech, play an important role in human communication. Automatic co-speech gesture generation is thus a key enabling technology for embodied conversational agents (ECAs), since humans expect ECAs to be capable of multi-modal communication. Research into gesture generation is rapidly gravitating towards data-driven methods. Unfortunately, individual research efforts in the field are difficult to compare: There are no established benchmarks, and each study tends to use its own dataset, motion visualisation, and evaluation methodology. To address this situation, we launched the GENEA Challenge, a gesture-generation challenge wherein participating teams built automatic gesture-generation systems on a common dataset, and the resulting systems were evaluated in parallel in a large, crowdsourced user study using the same motion-rendering pipeline. Since differences in evaluation outcomes between systems now are solely attributable to differences between the motion-generation methods, this enables benchmarking recent approaches against one another in order to get a better impression of the state of the art in the field. This paper reports on the purpose, design, results, and implications of our challenge.
- KSP 제안 키워드
- Common data, Embodied Conversational Agents(ECAs), Enabling technologies, Generation system, Gesture generation, Multi-modal communication, Rendering Pipeline, User study, crowdsourced evaluation, data-driven method, evaluation methodology