计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (24): 9-11.

• 博士论坛 • 上一篇    下一篇

一种新型音符起始点检测算法

桂文明1,2,邵 曦3,刘睿凡2   

  1. 1.南京理工大学 计算机科学与技术学院,南京 210094
    2.南京财经大学,南京 210046
    3.南京邮电大学,南京 210003
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-08-21 发布日期:2011-08-21

New algorithm for note onset detection

GUI Wenming1,2,SHAO Xi3,LIU Ruifan2   

  1. 1.School of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094,China
    2.Nanjing University of Finance & Economics,Nanjing 210046,China
    3.Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-21 Published:2011-08-21

摘要: 提出一种利用乐音频率变化特征进行音符起始点检测的算法,该算法基于连续小波变换(CWT)对音乐信号进行分解,分解后的信号频率和乐音频率分布相同。从分解后的信号中提取音符起始点特征,使用双边指数光滑和移动窗口归一化算法优化检测函数,产生音符起始点。

关键词: 连续小波变换, 双边指数光滑, 移动窗口归一化, 音符起始点

Abstract: This paper proposes a new algorithm for note onset detection,which is based on the Continuous Wavelet Transform(CWT) and the music knowledge.The musical signals are decomposed into the frequencies whose distribution are identical to music tones,and note onset features are extracted.The double side exponential smoothing method and normalization techniques based on moving window are employed to detect the onsets.

Key words: continue wavelet transform, double side exponential smoothing, moving window normalization, note onset detection