Abstract: Speech emotion information has nonlinear, redundancy and high dimension characteristics, the data has lots of noise, the traditional methods cannot eliminate the redundancy information and noise, so speech emotion recognition accuracy is quite low. In order to improve the accuracy of speech emotion recognition, this paper puts forward a speech emotion recognition model based on process neural networks strong nonlinear processing ability and wavelet analysisdenoising. The noise of speech signal is eliminated by wavelet analysis, the redundancy information is eliminated by the principal components analysis, the speech emotional signal is recognized by the process neural networks. Simulation results show that the average recognition rate of the process neural networks is higher than K neighbor by 13%, and higher than the support vector machine by 8.75%, therefore the proposed model is an effective speech emotion recognition tool.

Key words: motional feature, emotion recognition, neural network, Principal Component Analysis（PCA）

摘要： 语音情感信息具有非线性、信息冗余、高维等复杂特点，数据含有大量噪声，传统识别模型难以消除冗余和噪声信息，导致语音情感识别正确率十分低。为了提高语音情感识别正确率，利用小波分析去噪和神经网络的非线性处理能力，提出一种基于过程神经元网络的语音情感智能识别模型。采用小波分析对语音情感信号进行去噪处理，利用主成分分析消除语音情感特征中的冗余信息，采用过程神经元网络对语音情感进行分类识别。仿真结果表明，基于过程神经元网络的识别模型的识别率比K近邻提高了13%，比支持向量机提高了8.75%，该模型是一种有效的语音情感智能识别工具。

关键词: 情感特征, 情感识别, 神经网络, 主成分分析