Emotion Recognition from Audio-Visual Information based on Convolutional Neural Network

Abstract

In recent years., emotion recognition becomes a heavily researched field to consider in any project related to affective computing. Due to the almost limitless applications of this new discipline., the development of emotion recognition systems has emerged as a lucrative opportunity in the corporate sector. Emotion recognition can be detected in many ways., face., speech., text., gestures., etc. This paper proposes an emotion recognition approach using multiple information sources. Our approach involves both visual and speech information and it is based on Convolutional neural networks. The experiments prove the effectiveness of the proposed approach and the importance of combining visual with audio data.