GUO Wen-qiang1, QIU Tian-shuang1, ZHA Dai-feng1. Blind speech signals separation based on Borel measure peaks for under-determined mixtures[J]. 2007, (9): 22-26.DOI:
基于Borel测度峰值判定的欠定混合盲语音信号分离
摘要
简要介绍稳定分布的特征函数及其Borel测度表示
给出了Borel测度的估计方法
并利用Borel测度的峰值确定混合矩阵的基矢量
从而可以确定各个独立分量
实现信号的盲分离。计算机模拟和分析表明
这种算法是一种在高斯和分数低阶Alpha稳定分布噪声条件下具有良好韧性的独立分量分析与盲源分离方法
在盲语音混合信号的分离应用中也得到了很好的效果。
Abstract
The statistical characteristics of stable distribution was briefly introduced
and a new method for identifying the independent components of an Alpha-stable random vector for under-determined mixtures was proposed.The method was based on an estimate of the discrete spectral measure for the characteristic function of an Alpha-stable random vector.Simulations demonstrate that the proposed method can identify independent components and the basis vectors of mixing matrix in the so-called under-determined case of more sources than mixtures
and obtained the good effect in the speech signals separation application.