基于节奏和韵律调制谱特征的音乐流派分类  

Music Genre Classification Based on Modulation Spectrum Features of Rhythm and Rhyme

作　　者：庄严[1] 于凤芹[1] 

机构地区：[1]江南大学物联网工程学院,江苏无锡214122

出　　处：《计算机工程》2015年第1期186-189,共4页Computer Engineering

基　　金：国家自然科学基金资助项目(61075008)

摘　　要：音乐主要包括形成节奏的冲击成分和形成韵律的和声成分,直接从音乐信号中提取特征会受到这2种成分相互影响。利用节奏与和声在时频平面具有不同规律的特点,通过对音乐信号进行谱图滤波,分离出音乐中的打击成分与和声成分。对打击与和声谱图分别进行小波调制,得到表现音乐节奏和韵律谱规律的调制谱特征,将其作为音乐流派分类中的长时特征。仿真实验结果表明,分离后的打击与和声成分谱图清晰地表征了音乐节奏和韵律的特点和规律;对8类音乐流派提取打击与和声调制谱特征,经线性鉴别分析降维后利用支持向量机进行分类,分类准确率达到73.54%。Music is mainly composed of percussive component and harmonic component,and the former forms the rhythm while the latter forms melody and harmony. Extracting features from the music samples directly are affected by the interaction between the two components. As the rhythm and harmony presenting different distributions in the timefrequency plane,the percussive component and the harmonic component can be separated by applying filtering on the spectrogram. It modulates the percussive and harmonic spectrograms with wavelet respectively and then gets the music rhythm and rhyme modulation spectrum features,which describes the long-term mid-level features of music genres.Experimental results show that the music rhythm and rhyme features represent feature and rule of rhythm and rhyme after the percussive and harmonic spectrogram separation. And the classification accuracy is 73.54% for eight music genresclassification applying this method with Linear Discriminant Analysis（LDA） and afterward Support Vector Machine（SVM）.

关 键 词：谱图分离 中值滤波 小波调制谱 节奏和韵律 中级特征 音乐流派分类 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]