Welcome to this webinar arranged by WARA Media and Language where Taras Kucherenko, Research Scientist at EA Games, will talk about generation and evaluation of co-speech gestures for embodied conversational agents using deep learning.
If you wish to attend, please register using the link below.
Abstract
Humans use non-verbal behaviors to signal their intent, emotions, and attitudes in human-human interactions. Embodied conversational agents (ECA), therefore, need this ability as well in order to make interaction pleasant and efficient. An essential part of non-verbal communication is gesticulation. The task of hand gesture generation has been initially approached mainly by rule-based methods, but current state-of-the-art methods are data-driven, and we continue this line of research. In this talk, I will present my work addressing the two components of my thesis: generation and evaluation of co-speech gestures for embodied conversational agents using deep learning.
Bio Taras Kucherenko
Taras Kucherenko is currently a Research Scientist at EA Games. Recently he finished a Ph.D. at the KTH Royal Institute of Technology in Stockholm. His research is on machine learning models for non-verbal behavior generation, such as hand gestures and facial expressions. For his research papers, he received ICMI 2020 Best Paper Award and IVA 2020 Best Paper Award. Taras was also the main organizer of The GENEA (Generation and Evaluation of Non-verbal Behavior for Embodied Agents) Workshop both in 2020 and in 2021.