Group emotion estimation using Bayesian network based on facial expression and prosodic information

Abstract

Recently, there have been many studies on the activation of group communication, and it is important to easily and stably measure the states of group communication. We focus on group emotion expressed during conversation, and propose a method for estimating group emotion reliably using a Bayesian network based on both face image features and prosodic information. In the proposed method, group emotion is derived from estimation state values of individual emotions in the Bayesian network. The effectiveness of the proposed method was verified by performing experiments involving group conversation.