高斯条件下基于粒子滤波的声源定位  

Particle Filter for Acoustic Source Localization

作　　者：李彦翔[1] 刘庆华[1] 

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《电声技术》2009年第10期52-55,共4页Audio Engineering

基　　金：广西自然科学基金(0832007Z)

摘　　要：介绍了粒子滤波的基本思想和具体算法实现步骤,并将粒子滤波算法应用在声源定位中,解决了在高斯噪声环境下的声源定位问题。所提出的基于粒子滤波的声源定位方法,在高斯噪声情况下,甚至在低信噪比(SNR<-20dB)情况下,定位的均方根误差RMSE值均小于0.2m。PF（Particle Filter） is a new filtering method based on Bayesian estimation and Monte Carlo method, and can effectively cope with complicated nonlinear and/or non-Gaussian problems. The basic idea and algorithm description of particle filter are presented. Then, the PF is introduced into acoustic source localization. The rootmean-square error of this method is less than 0.2 meters in Gaussian noisy environment even in the environment of low SNR.

关 键 词：高斯噪声 粒子滤波 到达时间差 声源定位 均方根误差 

分 类 号：TN643[电子电信—电路与系统] O42[理学—声学]