基于隐马尔可夫模型的音乐分类  

Music classification based on Hidden Markov Models

作　　者：肖晓红[1] 张懿[2] 刘冬生[1] 欧阳春娟[1] XIAO Xiaohong;ZHANG Yi;LIU Dongsheng;OUYANG Chunjuan(School of Electronics and Information Engineering, Jinggangshan University, Ji’an, Jiangxi 343009, China;Department of Electronic Engineering, Tsinghua University, Beijing 100084, China)

机构地区：[1]井冈山大学电子与信息工程学院,江西吉安343009 [2]清华大学电子工程系,北京100084

出　　处：《计算机工程与应用》2017年第16期138-143,165,共7页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61462046);江西省教育厅科学技术研究项目(No.GD14559)

摘　　要：音乐类型(Genre)是应用最普遍的管理数字音乐数据库的方式,提出一种基于隐马尔可夫模型(Hidden Markov Models,HMMs)的音乐自动分类方案。在考虑传统的音色特征(Timbre)的同时,将另一重要特征节奏(Tempo)也加以考虑,并通过bagging训练两组HMM进行分类,达到了良好的效果。从结构、状态数和混合高斯模型数三个方面进行了参数优化,找到了最佳的HMM参数。在音乐数据集GTZAN上对传统模型和新模型分类效果进行了测试,结果表明考虑了节奏特征的HMM分类效果更佳。Music genre is one of the most common ways used in digital music database management.A music automatic classification scheme based on Hidden Markov Models(HMMs)is proposed.While considering traditional timbre,another important feature--Tempo is taken into consideration.Meanwhile,the bagging is used to train two groups of HMM for classification,which obtain good results.In this paper,optimized hyper-parameters in the HMM structure,the number of states and Gaussian mixtures,and find the best HMM parameters.Furthermore,the traditional model and original model are tested on the well-known GTZAN database.The results show that the proposed method considering tempo feature acquires better classification accuracy compared to the traditional model.

关 键 词：分类 音乐类型 节奏 隐马尔可夫模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]