Abstract: In this paper we describe an emotional human-machine interface as an anthropomorphic social agent which is able to comprehend emotions and react to emotional stimuli. We propose a neurobiologically inspired agent implementation that is based on mechanics of chemical and physiological processes within human brain. Implementation of model features simulation of neuromodulators such as dopamine, serotonin, and noradrenaline. Demonstration of emotions is achieved via combining aforementioned neuromodulators in different proportions. The Lȍvheim cube of emotions is used for this purpose. We also cover the topic of "uncanny valley" phenomenon. In conclusion of this paper we reached understanding of connection between mimics and motivation of individual. We have constructed realistic computation model which allows us to visualize agent's mimics in sync with his speech.

Abstract: Three-dimensional facial animation has been extensively studied, but the achievement of realistic, human-like performance has not yet been decided. This article discusses various approaches for generating animated facial expressions controlled by speech. Combining the considered approaches for both facial animation, and the identification of emotions and the creation of micro-facial expressions in one system, we get a solution suitable for tasks such as game video, avatars of virtual reality or any scenario in which a speaker, speech or language is not known in advance.

Abstract: In this paper, we study the process of evaluating the psychological portrait of a human for the purposes of enhancing the human-machine communication in the frame of the anthropomorphic social agent. We understand “psychological portrait” as the current emotional state of the interlocutor, which is evident by their way of talking and their choice of words. By correctly identifying human’s emotional state, the machine can issue an appropriate response. Our study further describes how the emotional state can be examined and how a proper response should be formed.