基于深度信念网络的语音情感识别的研究

Research of Speech Emotion Recognition Based on DBNs

针对语音情感识别中的特征提取的问题,提出了一种新的特征提取方式,利用深度神经网络(DNN)中的深度信念网络(DBNs)自动提取语音信号中情感特征.通过训练一个5层的深度信念网络提取语音情感特征,把连续多帧的语音并在一起,构成一个高维的特征,把深度信念网络训练完的特征作为非线性支持向量机(SVM)分类器的输入端,最终建立一个语音情感识别多分类器系统.其识别率为86.5%比传统的基于提取句子的时间构造、振幅构造、基频构造等特征的方法提高7%.

In view of feature extraction in speech emotion recognition problems,this paper proposed a new way of feature extraction,using DBNs in DNN to extract emotional features in speech signal automatically.By training a 5layers depth DBNs,to extract speech emotion feature and incorporate multiple consecutive frames to form a high dimensional feature.The features after training in DBNs were the input of non-linear SVM classifier,finally achieved speech emotion recognition multiple classifier system.The speech emotion recognition rate of the system reached 86.5%,which was 7%higher than the original method.