###
DOI:
Journal of Software:2009.20(zk):213-220

音乐检索特征库构建方法
李鹏,周明全,李娟,黎南杉
(北京师范大学 虚拟现实与可视化技术研究所,北京 100875;北京师范大学 信息科学与技术学院,北京 100875)
Music Retrieval Feature Database Construction Methods
LI Peng,ZHOU Ming-Quan,LI Juan,LI Nan-Shan
()
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 2800   Download 4808
Received:May 15, 2009    Revised:July 23, 2009
> 中文摘要: 合理的音乐特征库构建方法对于实现准确音乐检索具有重要意义.以基于内容音乐检索框架为基础,将音乐特征库的构建分为采用基音提取方法建库、采用乐谱信息建库和采用MIDI分析方法建库3种方式,并提出一种基音提取及后处理方法和MIDI分析方法实现音乐特征库的构建.实验结果表明,这两种建库方法是正确有效的,可以准确、快速地实现音乐特征库的构建.
Abstract:Construct music feature database properly is significant to accurate music retrieval. On the foundation of content-based music retrieval framework, this paper divides the database construct methods into pitch extraction, score information and MIDI analysis method. It proposes a pitch extraction, post-processing methods and MIDI analysis methods to implement the database construction. Experimental results show that the two methods are correct and effective, could construct a music database accurately and rapidly.
文章编号:     中图分类号:    文献标志码:
基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.60673100, 60736008 (国家自然科学基金); the Beijing Municipal Natural Science Foundation of China under Grant No.4081002 (北京市自然科学基金) Supported by the National Natural Science Foundation of China under Grant Nos.60673100, 60736008 (国家自然科学基金); the Beijing Municipal Natural Science Foundation of China under Grant No.4081002 (北京市自然科学基金)
Foundation items:
Reference text:

李 鹏,周明全,李 娟,黎南杉.音乐检索特征库构建方法.软件学报,2009,20(zk):213-220

LI Peng,ZHOU Ming-Quan,LI Juan,LI Nan-Shan.Music Retrieval Feature Database Construction Methods.Journal of Software,2009,20(zk):213-220