Técnicas de reconocimiento automático de emociones

Abstract

In this paper we present a summary of the main techniques for the automatic recognition of human emotions. We study the most important kind of emotions, centering on the specific emotions. We focus on the two most relevant ways in which emotions are studied: facial expressions from a video, and phonetic expressions from a speech. Since the type of emotions obtained from these two approaches could be different, the fusion of these different sources of information is one of the most interesting areas of research. We present a review of the statistical techniques used in emotion recognition. A fundamental task is the development of an appropriate database, with real audio-visual data, focus on emotion learning.