基于样本的流行歌曲关键段分割方法

张一彬, 周 杰, 边肇祺

电子学报 ›› 2006, Vol. 34 ›› Issue (2) : 220-225.

PDF(291 KB)
PDF(291 KB)
电子学报 ›› 2006, Vol. 34 ›› Issue (2) : 220-225.
论文

基于样本的流行歌曲关键段分割方法

  • 张一彬, 周 杰, 边肇祺
作者信息 +

Samples-Based Automatic Key Segment Extraction for Popular Song

  • ZHANG Yi-bin, ZHOU Jie, BIAN Zhao-qi
Author information +
文章历史 +

摘要

流行歌曲的关键段为歌曲中最能打动人、给人印象最深刻的一个完整片段.将它分割出来可用于音乐试听和基于内容的音乐分类、检索、管理.通过对人工截取的样本进行分析,本文提出了一种流行歌曲关键段自动分割方法.实验结果表明,此方法可以比较准确和有效地分割出流行歌曲中的关键段.

Abstract

We define the key segment of a popular song as the most impressive part in this song.It can be regarded as a perfect index or summary for this song,therefore it is much helpful for popular song's audition and management.We propose an effective algorithm for automatic key segment extraction based on the analysis of positive and negative samples of key segment extracted manually from a training database.An experiment is carried on a test database including 130 popular songs.Compared with manually extraction of key segments,the proposed algorithm has a rather satisfying performance.

关键词

数字娱乐 / 流行歌曲 / 音乐自动摘要 / 神经网络

Key words

digital entertainment / popular song / automatic music summary / neural network

引用本文

导出引用
张一彬, 周 杰, 边肇祺. 基于样本的流行歌曲关键段分割方法[J]. 电子学报, 2006, 34(2): 220-225.
ZHANG Yi-bin, ZHOU Jie, BIAN Zhao-qi. Samples-Based Automatic Key Segment Extraction for Popular Song[J]. Acta Electronica Sinica, 2006, 34(2): 220-225.
中图分类号: TP391   

基金

国家自然科学基金 (No.60573060,60205002,60332010); 北京市自然科学基金 (No.4042020)
PDF(291 KB)

2413

Accesses

0

Citation

Detail

段落导航
相关文章

/