Bayesian-Based Inference of Dialogist´s Emotion for Sensitivity Robots

We describe a method for sensitivity communication robots which infer their dialogist´s emotion. The method is based on the Bayesian approach: by using a Bayesian modeling for prosodic features. In this research, we focus the elements of emotion included in dialogist´s voice. Thus, as training datasets for learning Bayesian networks, we extract prosodic feature quantities from emotionally expressive voice data. Our method learns the dependence and its strength between dialogist´s utterance and his emotion, by building Bayesian networks. Bayesian information criterion, one of the information theoretical model selection method, is used in the building Bayesian networks. The paper finally proposes a reasoner to infer dialogist´s emotion by using a Bayesian network for prosodic features of the dialogist´s voice. The paper also reports some empirical reasoning performance.