基于小波包变换和小波阈值消噪的语音特征提取

作者：陈白 日期：2008-11-03/span> 浏览：3017 查看PDF文档

基于小波包变换和小波阈值消噪的语音特征提取

陈白
(燕山大学 电子实验中心,河北 秦皇岛 066004)

摘要：为了实现强噪声背景下语音信号的特征提取，根据小波变换的多分辨率特性，以及与人耳耳蜗滤波相一致的特性，利用小波包变换，在各语音特征频率段上，提取出包含丰富的非平稳信息的语音特征；并在小波包分解去噪的基础上，构造了模糊阈值函数，利用小波模糊阈值去噪，得到了信噪比较高的语音信号。研究结果表明，小波包变换和小波阈值去噪，较好地消除了强噪声背景下的噪声，并有效地提取出了语音信号特征。
关键词：小波包变换;语音特征提取;语音消噪;小波阈值消噪
中图分类号：TN912.3文献标识码：A文章编号：1001-4551(2008)09-0028-03

Phonic character extraction based on wavelet packet transform
and wavelet threshold denoising
CHEN Bai
(Electronic Experiment Center, Yanshan University, Qinhuangdao 066004, China)
Abstract: Aiming at realizing phonic character extraction at stronger noise background, wavelet packet Transform was used, and phonic character including plenty nonstationary information was extracted at phonic character frequency segments, based on the multi-resolution feature of wavelet transform, and its consistency with cochlea filtering. Fuzzy threshold function was constructed, and phonic signal with higher SNR was gained, using wavelet threshold denoising. Experimental results show that, noise is denoised and phonic character is extracted availably at a stronger noise background, using wavelet packet transform and wavelet threshold denoising.
Key words: wavelet packet transform; phonic character extraction; phonic denoising; wavelet threshold denoising
参考文献(Reference):
［1］YAN Ru-qiang, GAO R X. An efficient approach to machine health diagnosis based on harmonic wavelet packet transform ［J］. Robotics and Computer-Integrated Manufacturing,2005,21(4-5):291-301.
［2］华国刚,戴蓓倩,张钦,等.基于小波变换和平均周期的鲁棒性基音周期检测方法［J］.数据采集与处理, 2002,17(1):10-14.
［3］AZZALINI A, FARGE M, SCHNEIDER K. Nonlinear wavelet thresholding: a recursive method to determine the optimal denoising threshold［J］. Applied and Computational Harmonic Analysis,2005,18(2):177-185.
［4］李杰,丁宣浩.一种改进的小波阈值消噪方法［J］.广西工学院学报,2006,17(2):33-36.
［5］李玉,于凤芹,杨慧中,等.基于新的阈值函数的小波阈值去噪方法［J］.江南大学学报,2006,5(4):476-479.
［6］雷鹏.工厂自动控制系统的说话人识别模块实现［J］.电声技术,2002(10):7-10