基于粒子滤波的声源定位方法  

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：《计算机工程与应用》2010年第30期245-248,共4页Computer Engineering and Applications

基　　金：广西自然科学基金No.0832007Z~~

摘　　要：针对噪声与混响环境下的声源定位问题,采用了一种基于粒子滤波的麦克风阵列的声源定位方法。在粒子滤波框架下,将到达麦克风的语音信号作为观测信息,通过计算麦克风阵列波束形成器的输出能量来构建似然函数。实验结果表明,方法提高了声源定位系统的抗噪声与抗混响能力,即使在低信噪比强混响的环境下也能获得较高的定位精度。A sound source localization method based on microphone array is presented for acoustic source localization problem in noisy and reverberant environments.In the framework of particle filtering,the speech signal is served as the observation information,and likelihood function is constructed by the output power of beamformer.The results of simulation data and real data show that the proposed method can reliably confirm the acoustic source＇s position even in moderately reverberant rooms.Even in the environment of low SNR and strong reverberation,the adopted method can also give effectual localization.

关 键 词：混响环境 粒子滤波 可控波束形成 声源定位 均方根误差 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]