强噪声环境下自适应语音端点检测算法

林雪梅

doi:10.3969/j.issn.1007130X.2011.

计算机工程与科学 >

2011 , Vol. 33 >Issue 1: 94 - 96

DOI: https://doi.org/10.3969/j.issn.1007130X.2011.

论文

强噪声环境下自适应语音端点检测算法

展开

（湖南农业大学信息科学技术学院,湖南长沙 410128）

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。

收稿日期: 2010-05-20

修回日期: 2010-09-05

网络出版日期: 2011-01-25

基金资助

湖南省科技厅资助项目（2009nk3116）

收起

An Adaptive Voice Activity Detection Algorithm in Noisy Environments

Expand

(School of Information Science and Technology,Hunan Agricultural University,Changsha 410128,China)

Received date: 2010-05-20

Revised date: 2010-09-05

Online published: 2011-01-25

Fold

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

本文引用格式

林雪梅 . 强噪声环境下自适应语音端点检测算法[J]. 计算机工程与科学, 2011 , 33(1) : 94 -96 . DOI: 10.3969/j.issn.1007130X.2011.

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

参考文献

［1］韩立华, 王博, 段淑凤. 语音端点检测技术研究进展［J］. 计算机应用研究, 2010, 27(4):12201226.
［2］Rabiner L R,Sambur M R. An Algorithm for Determining the Endpoints of Isolated Utterances［J］. Bell System Technical Journal, 1975, 54(2):297315.
［3］Taboada J, Feijoo S, Balsa R, et al. Explicit Estimation of Speech Boundaries［J］. IEE Proceedings Science Measurement and Technology, 1994, 141(3):153159.
［4］He Qiang,Zhang Youwei. On Prefiltering and Endpoint Detection of Speech Signal［C］∥Proc of ICSP’98, 1998:749752.
［5］Li Qi, Zheng Jinsong, Tsai A, et al. Robust Endpoint Detection and Energy Normalization for RealTime Speech and Speaker Recognition［J］. IEEE Trans on Speech and Audio Processing, 2002, 10(3):146157.
［6］KyoungHo, Yang TaeYoung, Park KunJung, et al. Robust Voice Activity Detection Algorithm for Estimating Noise Spectrum［J］. Electronics Letters, 2002, 36(2):180181.
［7］Marzinzik M,Kollmeier B. Speech Pause Detection for Noise Spectrum Estimation by Tracking Power Envelope Dynamics［J］. IEEE Trans on Speech and Audio Processing, 2002, 10(2):109118.
［8］Beritelli F, Casale S, Serrano S. A LowComplexity SpeechPause Detection Algorithm for Communication in Noisy Environments［J］. European Trans on Telecommunications, 2004, 15(1):3338.
［9］王博, 郭英, 段艳丽,等. 基于倒谱特征的语音端点检测算法研究［J］. 信号处理, 2005, 21(4A):212215.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献