计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (36): 126-128.DOI: 10.3778/j.issn.1002-8331.2009.36.037

• 数据库、信号与信息处理 • 上一篇    下一篇

元音检测和最值点符号特征匹配的音乐检索

张 燕1,2,钱 博2,李燕萍3   

  1. 1.南京理工大学 计算机科学与技术学院,南京 210094
    2.金陵科技学院 信息技术学院,南京 211169
    3.南京邮电大学 通信与信息工程学院,南京 210003
  • 收稿日期:2009-08-20 修回日期:2009-09-25 出版日期:2009-12-21 发布日期:2009-12-21
  • 通讯作者: 张 燕

Music retrieval based on vowel detection and symbol feature representation

ZHANG Yan1,2,QIAN Bo2,LI Yan-ping3   

  1. 1.Department of Computer Science & Technology,Nanjing University of Science and Technology,Nanjing 210094,China
    2.Information Technology School of Jinling Institute of Technology,Nanjing 211169,China
    3.College of Telecommunication & Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Received:2009-08-20 Revised:2009-09-25 Online:2009-12-21 Published:2009-12-21
  • Contact: ZHANG Yan

摘要: 哼唱的随意性和音乐特征提取算法误差都会影响基于哼唱的音乐检索系统的性能。针对上述问题,利用元音帧检测获得较为精确的音符边界,实现音符分割;对分割后的音符提取相对音高和音长,实现符号描述;最后将哼唱片段中音高和音长最值点周围的符号描述作为特征与数据库中的数据进行匹配,得到最相似的候选音乐。实验表明该方法对未经训练的哼唱者的首位匹配正确率达到70%以上,匹配速度也大大优于传统方法,检索性能基本达到了实际应用的需求。

关键词: 音频检索, 音乐检索, 元音检测, 符号特征描述

Abstract: In query-by-humming systems,uncertainty can arise in query formulation due to user-dependent variability and machine-based errors.The paper proposes a new system,which using vowel detection for note segmentation.After that,the segmented humming audio is transcribed to symbols with pitch and duration information.At last,the transcribed audio is compared with the database and finds the closest melodic fragments.Experiment shows the retrieval accuracy is higher than 70% of best candidate with faster retrieval speed than traditional system,which achieves the requirement of practice application.

Key words: audio retrieval, music retrieval, vowel detection, feature representation with symbol

中图分类号: