Research on Speech Emotion Recognition Technology based on Deep and Shallow Neural Network

Speech emotion recognition has become a hot topic in the field of human-computer interaction. In order to improve the accuracy of emotion recognition, this paper proposes a new speech emotion recognition technology based on the combination of deep and shallow neural networks. First, the speech signal is preprocessed, then the parallel training sample set is established, and the Deep Belief Network (DBN) is used to automatically extract and recognize the speech emotion features. Finally, the shallow neural network is used to obtain the final recognition results. In order to evaluate the quality of the new method, we compared three systems to identify five emotions, and the experimental results show that the proposed method can effectively improve the accuracy of emotion recognition.