• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2011, Vol. 33 ›› Issue (1): 94-96.doi: 10.3969/j.issn.1007130X.2011.

• 论文 • 上一篇    下一篇

强噪声环境下自适应语音端点检测算法

林雪梅   

  1. (湖南农业大学信息科学技术学院,湖南 长沙 410128)
  • 收稿日期:2010-05-20 修回日期:2010-09-05 出版日期:2011-01-25 发布日期:2011-01-25
  • 通讯作者: 林雪梅 E-mail:540850786@qq.com
  • 作者简介:林雪梅(1967),女,辽宁大连人,讲师,研究方向为数据库、数据挖掘与计算机仿真。
  • 基金资助:

    湖南省科技厅资助项目(2009nk3116)

An Adaptive Voice Activity Detection Algorithm in Noisy Environments

LIN Xuemei   

  1. (School of Information Science and Technology,Hunan Agricultural University,Changsha 410128,China)
  • Received:2010-05-20 Revised:2010-09-05 Online:2011-01-25 Published:2011-01-25

摘要:

本文在分析基于短时能量的语音端点检测算法局限的基础上,引入短时信噪比SNR估计方法,并设计自适应的判决门限,提出一种自适应语音端点检测算法。通过对平稳高斯白噪声环境下信噪比从10dB到20dB的带噪语音信号进行的仿真实验表明,所提方法能更为准确地检测到语音的端点。

关键词: 端点检测, 自适应, 信噪比, 判决准则

Abstract:

The shortages of shorttime energy based voice activity detection method is analyzed first. Then a shorttime signaltonoise ratio (SNR) estimation method is introduced, and a new adaptive voice activity detection algorithm is proposed based on the design of the adaptive discriminative threshold. Simulations with a lot of Gaussian noisy speech signals ranging from 10dB to 20dB show that the comparatively accurate speech endpoints can be detected by the proposed method in different SNR environments.

Key words: voice activity detection;adaptive;signal to noise ratio;discriminative rules