Facial and speech Emotional Recognition based on Improved Deep Model

Abstract

In recent years, emotion recognition as a new method for natural human-computer interaction has attracted the attention of many researchers. Because the automatic recognition of emotion from speech or facial expressions alone has uncertainties; it is expected that emotion recognition based on the fusion of audio-visual information can be done with better accuracy. The purpose of this article is to present an efficient method for emotion recognition from emotional speech signals and images of emotional facial expressions, based on the SOAR cognitive science model. In this article, in order to implement the subsections of the SOAR model, stochastic deep learning has been used. In the proposed model, the RAVDESS database is used for testing and evaluation, and we have achieved 89.44% accuracy in the evaluation.