普通话语音情感识别的特征选择技术

Feature selection for emotion recognition of mandarin speech

针对情感声学特征在语音情感识别中的重要性问题,运用优先选择、序列前向、序列后向和逐步判别分析进行了特征选择.对说话人和文本均无关、说话人相关2组普通话情感语音进行特征选择,然后利用线性判别分析和支持向量机进行实际识别效果的分析比较.特征选择结果表明,基频、对数能量、语速和第一共振峰均值对普通话情感语音具有较强的判别能力,但情感声学特征的判别力随着说话人的不同而有所差异.特征选择方法比较实验表明,逐步判别分析比其他3种方法具有更高的平均准确率,当特征个数为9~12时分类器的平均准确率最高.效用分析表明,特征选择在小样本时更加有效.

In order to improve the accuracy of speech emotion recognition and reduce the feature dimension,four feature selection methods,i.e.promising first selection(PFS),sequential forward selection(SFS),sequential backward selection(SBS) and stepwise discriminant analysis(SDA) were employed to select acoustic features.After feature selection for the emotional mandarin database with speaker&text-independent group and speaker-dependent group,two classifiers: linear discriminant analysis(LDA) and support vector machi...