Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (27): 143-145.DOI: 10.3778/j.issn.1002-8331.2009.27.043

• 数据库、信号与信息处理 • Previous Articles     Next Articles

Speech detection algorithm based on C0 complexity and short-time energy

MA Wei-rong1,FENG Hong-wei1,LI Ning2   

  1. 1.College of Information Science and Technology,Northwest University,Xi’an 710127,China
    2.School of Software,Dalian University of Technology,Dalian,Liaoning 116023,China
  • Received:2008-05-26 Revised:2008-08-06 Online:2009-09-21 Published:2009-09-21
  • Contact: MA Wei-rong

基于C0复杂度和能量的语音端点检测算法

马伟荣1,冯宏伟1,李 宁2   

  1. 1.西北大学 信息科学与技术学院,西安 710127
    2.大连理工大学 软件学院,辽宁 大连 116023
  • 通讯作者: 马伟荣

Abstract: Complexity measure is an important nonlinear property of the signal sequence.Speech detection methods based on complexity measures have nonlinear properties.This paper proposes a new speech detection method,which improves the traditional C0 complexity and combines with enhanced short-time energy.Simulation results indicate that the method has a strong robust to noise and is able to reliably detect the onset and offset of speech even for low SNR such as 0 dB situation.

Key words: endpoint detection, short-time energy, spectral subtraction, complexity

摘要: 复杂性测度是反映信号序列的一个重要的非线性特征,复杂性测度的语音端点检测技术具有非线性技术的本质特征。对C0复杂度作出改进,并与增强后的短时能量相结合,提出了一种更有效的端点检测算法——C0复杂度能量的语音端点检测方法。实验证明,该算法对噪声有很强的鲁棒性,在低信噪比(0 dB)下仍能准确地检测出语音段。

关键词: 端点检测, 短时能量, 谱减法, 复杂性测度

CLC Number: