Research on speech emotion recognition system in E-Learning

Aiming at emotion deficiency in present E-Learning system, a lot of negative effects were analyzed and corresponding countermeasures were proposed. Basing on it, 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 showed that neural networks was effective in emotion recognition, and we achieve a recognition rate of approximately 50% when testing eight emotions besides, other key techniques of realizing the system such as tracking the change of emotion state and adjusting teaching strategies were also introduced.