基于最优平滑和统计最小的语音增强  

Speech Enhancement Based on Optimal Smoothing and Minimum Statistics

作　　者：姜琳峰[1] 石鸿凌[1] 孙洪[1] 

机构地区：[1]武汉大学电子信息学院,湖北武汉430072

出　　处：《武汉大学学报（理学版）》2004年第1期113-117,共5页Journal of Wuhan University:Natural Science Edition

基　　金：国家自然科学基金资助项目(60072041)

摘　　要：针对传统最优平滑和统计最小的噪声估计方法存在较大搜索延时的缺点,提出了反向搜索噪声估计算法,从而在不需要语音活性检测的基础上有效地解决了搜索延时问题,并且运用反向搜索噪声估计器构造了新的语音增强系统.实验结果显示,该系统使语音得到进一步的增强,而且提高了噪声估计的精确度,具有一定的实用价值.The noise estimator is a very important component of the speech enhancement systems, especially if the algorithm should be capable of handling non-stationary noise. Based on the optimally smoothed power spectral density estimate and the analysis of the statistics of spectral minima an unbiased noise estimator is developed. But the noise jump is tracked with a large delay. So reverse estimator is developed for improving the accuracy of noise estimator. Reverse estimator is used in speech enhancement system with traditional Spectral Subtraction. In practice, estimated noise is the maximum of both noise estimators. The method can improve the intelligibility of speech. So it is a practical method.

关 键 词：最优平滑 统计最小 语音增强 反向搜索 谱减法 噪声估计算法 

分 类 号：TN912.35[电子电信—通信与信息系统]