基于LS-SVM的情感语音识别

Speech emotion recognition based on LS-SVM

提出了一种基于LS-SVM的情感语音识别方法。即先提取实验中语音信号的基频,能量,语速等参数为情感特征,然后采用LS-SVM方法对相应的情感语音信号建立模型,进行识别。实验结果表明,利用LS-SVM进行基本情感识别时,识别率较高。

The dissertation proposed an approach for emotional speech recognition based on LS-SVM. First, pitch frequency, energy, speech rate parameters extracted from speech signals as emotional features. Then emotional speech modeling is established with LS-SVM method. Experimental results show that, basic emotion recognition can get high recognition rates.