基于子空间域的自适应小字典的语音增强  

Subspace domain based speech enhancement of adaptive small dictionary

作　　者：裴俊华 贾海蓉[1] PEI Junhua;JIA Hairong(College of Information Engineering,Taiyuan University of Technology,Jinzhong 030600,China)

机构地区：[1]太原理工大学信息工程学院,山西晋中030600

出　　处：《现代电子技术》2019年第1期46-50,共5页Modern Electronics Technique

基　　金：国家自然科学基金项目(61371193);山西省自然科学基金项目(201701D121058)~~

摘　　要：针对传统小字典的语音增强算法在消除噪声时导致语音失真的问题,提出一种子空间域的自适应小字典的语音增强算法。首先,在子空间域中利用带噪语音信号的特征值构造过完备的小字典,使得该字典对信号失真和残留噪声具有很好的调控机制,即在消除噪声的同时为保证信号失真尽可能的小提供了可能;其次,通过过完备的小字典对带噪语音的特征值用K奇异值分解(K-SVD)算法不断进行稀疏表示和字典更新,其中在正交匹配追踪(OMP)算法中设置相关性阈值与能量阈值来自适应控制重构阶段及迭代次数,减少重构时间。在不同的噪声背景下的实验结果表明,与文献算法相比,新算法的增强语音的SNR和PESQ较高,减少了语音失真,提高了语音质量。Since the traditional speech enhancement algorithm of small dictionary has the problem of speech distortion for noise elimination,a speech enhancement algorithm based on adaptive small dictionary in subspace domain is proposed.A over-completed small dictionary is constructed by using the eigenvalues of noisy speech signal in the subspace domain to make the dictionary have perfect control mechanism for signal distortion and residual noise,which is possible to minimize the distortion of the signal while eliminating the noise.The K singular value decomposition(K-SVD)algorithm is used for sparse representation and dictionary updating for the noisy speech by means of over-complete small dictionary.The correlation threshold and energy threshold are set in orthogonal matching pursuit(OMP)algorithm to adaptively control the reconstruction and iteration times,and reduce the reconstruction time.The experimental results show that,in comparison with the algorithms given in literatures,the new algorithm under different noise backgrounds has higher SNR and PESQ,and can reduce the speech distortion and improve the speech quality.

关 键 词：语音增强 小字典 子空间 K-SVD OMP 阈值 

分 类 号：TN912.35-34[电子电信—通信与信息系统]