期刊文献+

Implementation of an Autocorrelation Pitch Detector in Application to Query by Humming

Implementation of an Autocorrelation Pitch Detector in Application to Query by Humming
下载PDF
导出
摘要 A pitch detector for application in query by humming (QBH) is implemented in this paper. This algorithm is made up of two parts: note segmentation and pitch detection. In the first part, voiced/silence decision is made on each segment of the input signal by a pattern recognition approach, and further, the preparatory note borders are obtained; then, via analysis of the instantaneous energy contour, the adjacent notes that adhere to each other are separated. In the second part, pitch is estimated for all frames contained in a note's duration by an autocorrelation method and the mean of these pitch values is taken as the average pitch of this note. Moreover, in order to remove the effect of formant structure, a nonlinear preprocessing is adopted in the pitch detection part and the autocorrelation function is properly weighted before peak picking. Finally, hummings of several experimenters with different voice characters are recorded to test this pitch detector, whose efficiency and reliability are proved by the results. A pitch detector for application in query by humming (QBH) is implemented in this paper. This algorithm is made up of two parts: note segmentation and pitch detection. In the first part, voiced/silence decision is made on each segment of the input signal by a pattern recognition approach, and further, the preparatory note borders are obtained; then, via analysis of the instantaneous energy contour, the adjacent notes that adhere to each other are separated. In the second part, pitch is estimated for all frames contained in a note's duration by an autocorrelation method and the mean of these pitch values is taken as the average pitch of this note. Moreover, in order to remove the effect of formant structure, a nonlinear preprocessing is adopted in the pitch detection part and the autocorrelation function is properly weighted before peak picking. Finally, hummings of several experimenters with different voice characters are recorded to test this pitch detector, whose efficiency and reliability are proved by the results.
出处 《Wuhan University Journal of Natural Sciences》 EI CAS 2005年第3期539-544,共6页 武汉大学学报(自然科学英文版)
基金 SupportedbytheNationalNaturalScienceFoun dationofChina(50099620)andthe863HighTechnologyProjectof China(2001AA132050)
关键词 Key words autocorrelation pitch detector query by humming note segmentation Key words autocorrelation pitch detector query by humming note segmentation
  • 相关文献

参考文献4

  • 1Rabi ner L R.On the Use of Autocorrelation Anal ysis for Pitch Detection[].Acoustics Speech and Si gnal Processing IEEE.1977
  • 2Atal B S,Rabi ner L R.A Pattern Recognition Approach to Voiced-Unvoiced-Silence Classification with Applications to Speech Recognition[].Acoustics Speech and Si gnal Processing IEEE.1976
  • 3Foote J.An Overvie w of Audio Infor mation Retrieval[].Multimedia Systems.1999
  • 4Yong D C.Pitch Post-Processi ng Techni que Based on Robust Statistics[].Electronics Letters IEEE.2002

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部