首页 | 本学科首页   官方微博 | 高级检索  
     检索      

弱稀疏语音信号的欠定盲分离
引用本文:和继威,刘郁林,王 开,李 力.弱稀疏语音信号的欠定盲分离[J].太赫兹科学与电子信息学报,2011,9(6):765-769.
作者姓名:和继威  刘郁林  王 开  李 力
作者单位:重庆通信学院DSP实验室;重庆市教育考试院;
摘    要:为解决弱稀疏语音信号的欠定盲分离问题,根据语音信号的部分W-分离正交性,提出一种基于单源主导区间的混合矩阵盲估计方法。该方法根据单源主导区间的性质,通过二元行矢量提取单源观测样本,对单源观测样本进行K均值聚类和主成分分析来估计混合矩阵。仿真结果表明,提出的方法可有效提高分离语音的性能,与直接利用K-PCA方法相比,分离语音的平均信噪比提高了10 dB左右。

关 键 词:欠定盲分离  弱稀疏  单源主导区间  W-分离正交性
收稿时间:2011/1/12 0:00:00
修稿时间:2011/3/4 0:00:00

Underdetermined blind separation for weak sparse speech signals
HE Ji-wei,LIU Yu-lin,WANG Kai and LI Li.Underdetermined blind separation for weak sparse speech signals[J].Journal of Terahertz Science and Electronic Information Technology,2011,9(6):765-769.
Authors:HE Ji-wei  LIU Yu-lin  WANG Kai and LI Li
Institution:HE Ji-wei1,LIU Yu-lin1,WANG Kai1,LI Li2(1.Chongqing Communication College,Chongqing 400035,China,2.Chongqing Education Examination College,China)
Abstract:In order to solve the problem of underdetermined blind speech separation for weak sparse speech signals,according to the partial approximate W-disjoint orthogonality of weak sparse speech signals,a blind mixing matrix estimation method is proposed based on single-source dominated areas.In this method,according to the property of the single-source dominant areas,single-source observational samples are extracted by a binary row vector;then the mixing matrix is estimated by K means clustering and Principal Com...
Keywords:underdetermined blind separation  weak sparse  single-source dominant area  W-disjoint orthogonality  
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《太赫兹科学与电子信息学报》浏览原始摘要信息
点击此处可从《太赫兹科学与电子信息学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号