基于计算听觉场景分析的改进清音分离方法  

An Improved Unvoiced Speech Segregation Based on Computational Auditory Scene Analysis

作　　者：王雨[1] 林家骏[1] 袁文浩[1] 陈宁[1] 

机构地区：[1]华东理工大学信息科学与工程学院,上海200237

出　　处：《华东理工大学学报（自然科学版）》2014年第2期212-217,共6页Journal of East China University of Science and Technology

基　　金：国家自然科学基金(61271349)

摘　　要：基于计算听觉场景分析(CASA)的单通道语音分离方法在浊音分离领域已发展得较为成熟,然而由于清音信号具有较小的能量且不包含周期性基音特征,因此清音分离具有较大的困难。根据噪声信号分布的不确定性和不稳定性,提出了基于CASA和谱减的改进清音分离方法。改进方法在剔除了浊音块后,通过基于距离加权的残余噪声估计算法得到每个清音单元中所包含的噪声能量,对每个清音单元进行谱减算法并标记,进一步剔除残余噪声单元,提取出清音信号。实验结果证明:与传统清音分离方法相比,改进方法对时变性残余噪声能量的估计结果更加精确,更能提高清音分离的有效性。Monaural speech segregation based on computational auditory scene analysis（CASA）has been deeply developed in voiced speech segregation.However,it is much difficult to segregate unvoiced speech,due to its weak energy and lack of pitch period feature.Aiming at the uncertainty and unstability of background noise,an improved method for unvoiced speech segregation is proposed.After removing voiced speech segments,this method estimates the noise energy in each unvoiced segments by means of distance-weighted noise estimation approach algorithm.Then,the spectral subtraction is utilized to extract and label the target unvoiced units.Compared with conventional unvoiced speech segregation method,the proposed method can improve the accuracy of residue noise estimation and attain better performance for unvoiced speech segregation.

关 键 词：清音分离 计算听觉场景分析 谱减 残余噪声估计 

分 类 号：TN912.3[电子电信—通信与信息系统]