作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (10): 250-252. doi: 10.3969/j.issn.1000-3428.2012.10.077

• 开发研究与设计技术 • 上一篇    下一篇

一种适用于非特定哼唱方式的起音点检测算法

郑玉婷,张文俊,韩 彪   

  1. (上海大学影视艺术技术学院,上海 200072)
  • 收稿日期:2011-09-19 出版日期:2012-05-20 发布日期:2012-05-20
  • 作者简介:郑玉婷(1986-),女,硕士研究生,主研方向:语音识别;张文俊,教授、博士生导师;韩 彪,硕士研究生
  • 基金资助:
    上海大学研究生创新基金资助项目;上海大学影视与传媒产业研究基地基金资助项目(SHUCX112309)

Onset Detection Algorithm Suited for Non-specific Humming Way

ZHENG Yu-ting, ZHANG Wen-jun, HAN Biao   

  1. (School of Film & TV Arts and Technology, Shanghai University, Shanghai 200072, China)
  • Received:2011-09-19 Online:2012-05-20 Published:2012-05-20

摘要: 针对现有音符起音点检测算法对非特定哼唱方式分割效果不佳的现状,提出一种新的基于音高的频谱差异算法。结合哼唱音高的变化特性,利用频谱差异算法、滑动窗平均滤波滤除冗余频谱能量干扰,降低过分割、误分割的检测错误。实验结果表明,该算法的检测准确率达80%,优于现有起音点检测算法。

关键词: 起音点检测, 音符分割, 滑动窗平均滤波, 哼唱检索, 峰值点提取

Abstract: A pitch based Spectral Flux(SF) algorithm is proposed for detecting the onset times of musical notes in humming signals. By using sliding window average filtering, SF algorithm and the feature of pitch change, the proposed algorithm can effectively filter the interference of redundant spectral energy, greatly reduce segmentation errors and achieve good detection improvement for those consecutively singing words. Experimental results show that the detection accuracy rate reaches 80%, better than other well used detection algorithms.

Key words: onset detection, note segmentation, sliding window average filtering, Query by Humming(QBH), peak point extraction

中图分类号: