电子学报 ›› 2017, Vol. 45 ›› Issue (4): 1000-1011.DOI: 10.3969/j.issn.0372-2112.2017.04.032

• 综述评论 • 上一篇    下一篇

复调音乐主旋律提取方法综述

张维维1,2, 陈喆1, 殷福亮1, 张俊星2   

  1. 1. 大连理工大学信息与通信工程学院, 辽宁大连 116024;
    2. 大连民族大学信息与通信工程学院, 辽宁大连 116600
  • 收稿日期:2016-01-29 修回日期:2016-07-28 出版日期:2017-04-25
    • 作者简介:
    • 张维维 女,辽宁大连人,1981年5月生,大连理工大学在读博士生,大连民族大学讲师.主要研究方向为音乐信号处理,音乐信息检索.Email:zhangww@dlnu.edu.cn;陈喆 男,黑龙江省泰来人,1975年11月生,大连理工大学副教授.主要研究方向为数字信号处理、语音处理、图像处理、宽带无线通信技术.E-mail:zhechen@dlut.edu.cn
    • 基金资助:
    • 国家自然科学基金 (No.61172107,No.61172110); 国家863高技术研究发展计划 (No.2015AA016306); 辽宁省教育厅科学研究一般项目 (No.L2015135); 中央高校基本科研业务费 (No.DUT13LAB06,No.DC201502060404)

Review on Melody Extraction from Polyphonic Music

ZHANG Wei-wei1,2, CHEN Zhe1, YIN Fu-liang1, ZHANG Jun-xing2   

  1. 1. School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, Liaoning, China;
    2. School of Information and Communication Engineering, Dalian Minzu University, Dalian 116024, Liaoning, China
  • Received:2016-01-29 Revised:2016-07-28 Online:2017-04-25 Published:2017-04-25
    • Supported by:
    • National Natural Science Foundation of China (No.61172107, No.61172110); National High-tech R&D Program of China  (863 Program) (No.2015AA016306); Research Project of Education Department of liaoning Province  (General Program) (No.L2015135); Fundamental Research Funds for the Central Universities (No.DUT13LAB06, No.DC201502060404)

摘要:

主旋律提取在音乐检索、乐谱抄录、翻唱识别等领域具有广泛应用.复调音乐频谱结构复杂多样,音高变化范围广,因此复调音乐的主旋律提取较为困难.本文综述了复调音乐主旋律提取研究进展,对复调音乐主旋律提取方法进行分类,阐述了典型方法,介绍了主旋律提取的评价指标,给出了最新MIREX主旋律提取评测结果,说明了主旋律提取面临的主要挑战,并对主旋律提取技术发展方向进行了展望.

关键词: 主旋律提取, 复调音乐, 多声部音乐, 音乐信号处理, 音乐信息检索

Abstract:

Melody extraction is to automatically extract the melody from a given piece of polyphonic music,and has been widely applied in music retrieval,score transcription,cover song identification and so on.Melody extraction from digital polyphonic music is reviewed in this paper.Firstly,the methods used for melody extraction are classified.Then,the representative methods are elaborated in detail,evaluation methodologies are presented,and the most recently MIREX melody extraction competition results are shown.Finally,the existing challenges are summarized,and the future research directions are provided.

Key words: melody extraction, polyphonic music, multi-part music, music signal processing, music information retrieval

中图分类号: