A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020
| Autor: | Kucherenko, Taras, Jonell, Patrik, Yoon, Youngwoo, Wolfert, Pieter, Henter, Gustav Eje |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1145/3397481.3450692 |
| Popis: | 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. Comment: Accepted for publication at the 26th International Conference on Intelligent User Interfaces (IUI'21). 11 pages, 5 figures |
| Databáze: | arXiv |
| Externí odkaz: |
|