Applying von Mises Distribution to Microphone Array Probabilistic Sensor Modelling

This paper deals with the problem of localizing and tracking a moving speaker over the full range around the mobile robot. The proposed algorithm is based on estimating the time difference of arrival by maximizing the weighted cross-correlation function in order to, by series of geometrical calculation, determine the azimuth angle of the detected speaker. A post processing technique is proposed in which each of these microphone-pair determined azimuths are further combined into a mixture of the von Mises distributions, thus producing a practical probabilistic representation of the microphone array measurement. It is shown that this distribution is inherently multimodal and that the system at hand is non-linear, which required a discrete representation of the distribution function by means of particle filtering. Experiments were conducted and the results show that the algorithm can reliably and accurately localize and track a moving sound source.