Speech Emotion Recognition Using Gaussian Mixture Model

摘要：

　　The importance of automatically recognizing emotions in human speech has grown with the increasing role of spoken language interfaces in human-computer interaction applications.In this paper,a emotion classification method base on GMM is presented.Five primary human emotions,including anger,surprise,happiness,neutral and sadness,are investigated.For speech emotion recognition,we combined 60 basic features to form the feature vector.Finally,the features of the speech were extracted by PCA were sent into the improved GMM for classification and recognition.Results show that the selected features are robust and effective for the emotion recognition.

关键词： Speech Emotion Recognition Wavelet transform MFCC PCA GMM

作者: Xianglin Cheng Qiong Duan

作者单位: Computer Engineer Department Zhongshan Polytechnic Zhongshan,China Basic Department,Zhongshan Polytechnic Zhongshan,China

会议类型: 国际会议

会议名称: 2012 2nd International Conference on Computer Application and System Modeling(2012第二届计算机应用与系统建模国际会议)(ICCASM-2012)

会议地点: 沈阳

会议语种:英文

页码: 1222-1225

在线出版日期: 2012-07-27（万方平台首次上网日期，不代表论文的发表时间）