Abstract
We propose a novel method for inferring state transitions from non participants to participants in free-style conversational interaction using physical behaviors acquired from cameras and a microphone. The existing methods do not consider non-participants and bystanders who play important roles in the interaction. In the research field of cognitive science, the existing methods consider the psychological aspects of changing from the non-participants to the participant. However, the existing methods cannot be easily implemented because inferring the psychological aspects is a very difficult task. Instead of using the psychological aspects, our method exploits physical behaviors such as standing position, facial direction, and audio direction. We analyzed the parameters of the behaviors to increase the performance of inferring the state transitions using datasets collected in the poster presentations.
