MRecGen: Multimodal Appropriate Reaction Generator
This enables more natural human-computer interaction by generating appropriate behaviors for virtual agents or robots.
The paper tackles the challenge of generating multiple appropriate verbal and non-verbal human reactions to a given behavior, resulting in a framework that produces synchronized text, audio, and video streams for realistic human-style responses.
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour. This paper proposes the first multiple and multimodal (verbal and nonverbal) appropriate human reaction generation framework that can generate appropriate and realistic human-style reactions (displayed in the form of synchronised text, audio and video streams) in response to an input user behaviour. This novel technique can be applied to various human-computer interaction scenarios by generating appropriate virtual agent/robot behaviours. Our demo is available at \url{https://github.com/SSYSteve/MRecGen}.