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, speech emotion recognition system is proposed in the paper. Then we introduce a systematic feature selection approach, which involves the application of sequential forward selection with a general regression neural network in conjunction with a consistency-based selection method. The selected features are employed as the input to a modular neural network to realize the classification of emotions. Our simulation experiment results show that the proposed system gives high recognition performance.