基于LMS自适应滤波的耳语音增强的研究  

Speech Enhancement Algorithm Based on LMS Adaptive Filtering in Chinese Whispered Speech

作　　者：孙静[1] 陶智[1] 顾济华[1] 赵鹤鸣[2] 

机构地区：[1]苏州大学物理科学与技术学院,江苏苏州215006 [2]苏州大学电子信息学院,江苏苏州215006

出　　处：《通信技术》2007年第12期394-396,共3页Communications Technology

基　　金：国家自然科学基金(批准号:60572076);江苏省高校自然科学研究计划项目(05JKB510113)

摘　　要：文中针对带噪的耳语音提出了一种LMS自适应滤波的耳语音增强算法。首先采用谱减法得到一个增强耳语音信号,取得较好的谱包络后对增强信号进行LMS自适应滤波,消除由谱减法产生的音乐噪声。结果表明,采集到的耳语音信号的质量得到明显提高,即使在低信噪比的情况下,信噪比也能提高20dB左右。This paper introduces a method based on the combination of spectral subtraction and LMS adaptive filtering in the enhancement .of Chinese whispered speech. First, an enhanced whispered speech by spectral subtraction is obtained, then the LMS adaptive filtering is applied to the enhanced signal to decrease the musical noise. The result shows that the quality of whispered speech is obviously enhanced and the SNR output can be improved by 20 dB even if the SNR input is low. The algorithm can result in SNR improvement.

关 键 词：耳语音 语音增强 自适应滤波 谱减法 

分 类 号：TN912.3[电子电信—通信与信息系统]