Resaerch On Technique Of Speech Emotion Recognition

Along with rapid development of Human Computer Interaction system, emotion in speech is a topic that has received much attention during the last few years, in the context of speech synthesis as well as in automatic speech recognition. The study on the speech emotion recognition has found very important realistic values in such aspects as enhancing the intelligence and humanity of computer, developing new human-machine environment, improving speech recognition results. The main goal of this thesis is to search the most useful features with analyzing the features related with emotions, and find a recognition model to make full use of these features.Firstly, we study the construction of emotion-speech template database, and analyze the common features such as pitch, energy and formant. After choosing the useful features by using fuzzy entropy effectiveness analysis, we get better performance with the application of neural network. In addition, we propose some more efficient features such as speech rate, pitch slope, Mel-Frequency Cepstral Coefficients and its transient parameters, and design a processing model based on vector quantization for cepstral features to fusing different features. Finally, this thesis constructs the system of speech emotion recognition by importing the processed cepstral features to neural network model, and proves the efficiency of the proposed method according to the experiments.