语音/音乐自动分类中的特征分析  

Feature Analysis for Speech/Music Automatic Classification

作　　者：卢坚[1,2] 陈毅松[1,2] 孙正兴[1,2] 张福炎[1,2] 

机构地区：[1]南京大学计算机科学与技术系,南京210093 [2]南京大学软件新技术国家重点实验室,南京210093

出　　处：《计算机辅助设计与图形学学报》2002年第3期233-237,共5页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金 (6990 3 0 0 6)资助

摘　　要：综合分析了语音和音乐的区别性特征 ,包括音调、亮度、谐度等感觉特征与 MFCC(Mel- Frequency CepstralCoefficients)系数等 ,提出一种 left- right DHMM(Discrete Hidden Markov Model)的分类器 ,以极大似然作为判别规则 ,用于语音、音乐以及它们的混合声音的分类 ,并且考察了上述特征集合在该分类器中的分类性能 .实验结果表明 ,文中提出的音频特征有效、合理 。Discriminating features between speech and music are analyzed, including perceptual features like pitch, brightness and harmonicity, etc, and Mel Frequency Cepstral Coefficients (MFCC). Their performances are evaluated in a left right discrete HMM based audio classifier, which is used to classify audio into speech, music, their mixed sound and such like three categories with maximum likelihood criterion. The experiment results show that the features selected are effective for speech/music classification, and the classification accuracy is excellent.

关 键 词：特征分析 隐马尔可夫模型 语音 音乐 自动分类 语音识别 音频信号 

分 类 号：TN912.34[电子电信—通信与信息系统]