Speech Emotion Recognition in E-learning System Based on Affective Computing

Aiming at emotion deficiency in present E-learning system, a lot of negative effects were analyzed and corresponding countermeasures were proposed In this paper we combined affective computing with the traditional E-learning system. The model of E-learning system based on affective computing was constructed by using speech emotion, which took speech feature as input data. Our simulation experiment results show that neural networks is effective in emotion recognition, and we achieved a recognition rate of approximately 50% when testing eight emotions. Other key techniques of realizing the system such as tracking the change of emotion state and adjusting teaching strategies were also introduced in addition.