小波消噪阈值算法优化-声学技术.pdfVIP

第 28 卷第 4 期 声 学 技 术 Vol.28, No.4 2009 年 8 月 Technical Acoustics Aug., 2009 小波消噪阈值算法优化 1 2 田玉静 ，左红伟 (1. 青岛理工大学现代教育技术中心，青岛 266033 ；2. 青岛理工大学土木工程学院，青岛 266033) 摘要：在研究小波固定阈值消噪方法，讨论阈值估计经验公式的基础上，针对加性噪声小波变换后的统计特征，提 出了一种自适应阈值优化算法，该算法可以较准确地估计噪声水平，在消噪的同时保留语音信号中的弱特征成分。 通过仿真实验验证，优化算法较传统算法能够更加有效地消除语音噪声，获得最大信噪比。 关键词：小波阈值消噪；阈值算法；优化算法；阈值函数 中图分类号：TN713.7 文献标识码：A 文章编号：1000-3630(2009)-04-0503-04 DOI 编码：10.3969/j.issn1000-3630.2009.04.015 Optimization threshold algorithm of wavelet de-noising 1 2 TIAN Yu-jing , ZUO Hong-wei (1. Modern Education and Technology Center, QingDao Technological University., Qingdao 266033, China; 2. School of Civil Engineering, Qingdao Technological University, QingDao 266033, China) Abstract: An adaptive optimization threshold algorithm is presented based on the experiential wavelet threshold expressions after the classical wavelet threshold de-noising methods are studied. According to the statistical characteristics of the wavelet noise, the scales of noise threshold are estimated exactly with the optimization algo- rithm, the weak features of speech signal can be preserved effectively and the noise is eliminated adequately at the same time. The simulation result shows a better effect of the optimization algorithm on noise reduction than the conventional algorithm, and an optimal signal to noise ratio could be obtained. Key words: wavelet threshold de-noising; threshold algorithm; optimi