强噪声环境下基于改进粒子滤波的麦克风阵列定位  

Acoustic Source Localization Based on Iterative Unscented Particle Filter

作　　者：吴迪[1] 唐勇奇[1] 

机构地区：[1]湖南工程学院电气信息学院,湘潭411101

出　　处：《湖南工程学院学报（自然科学版）》2016年第1期1-5,共5页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：国家科技支撑计划资助项目(1214ZGA008);国家自科基金资助项目(61263031);湖南省重点学科建设资助项目(081101);重庆市教委自然科学基金资助项目(KJ1400628);湖南工程学院博士科研启动基金(15045)

摘　　要：针对噪声和混响环境下说话人定位不准确的问题,提出了一种基于迭代无味粒子滤波的麦克风阵列声源定位方法.利用迭代无味卡尔曼滤波产生的建议分布函数对粒子滤波算法进行改进形成迭代无味粒子滤波,在该算法的框架下通过计算麦克风阵列波束形成器的输出能量构造似然函数.实验结果表明,该方法提高了说话人的定位精度,增强了说话人跟踪系统的抗噪声和抗混响能力.In order to solve the problem of inaccurate localization in noise and reverberation environment, a new microphone array sound source localization method based on Iterative Unscented Particle Filter is pro- posed in this paper. First, the Iterative Unscented Particle Filter is introduced to the acoustic source locali- zation. Then, the likelihood function is constructed by calculating the microphone array＇s output energy in the framework of the improved particle filtering algorithm. Finally, the experiment results show that the proposed location method can not only improve the positioning accuracy, but also enhance the ability of a- coustic source tracing system to resist noise and reverberation.

关 键 词：说话人定位 迭代无味粒子滤波 麦克风阵列 建议分布函数 似然函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]