PIDM: Personality-Aware Interaction Diffusion Model for Gesture Generation

In a dyadic conversation, the behaviors of one participant, such as nodding and smiling, are influenced by those of the conversation partner. The velocity and magnitude of motion during conversation are also affected by the personality traits of each participant. In this paper, we propose the personality-aware interaction diffusion model (PIDM) for a dyadic conversation. PIDM generates interaction behaviors based on the masking features of all participants and participants’ personalities. We apply PIDM to the motion generation during a dyadic conversation, and the differences in the generated results according to the personality are investigated. The results suggested that PIDM can change the distribution of generated behaviors by adjusting the extraversion which is the one parameter of the Big Five.