A Multiple Hypothesis Gaussian Mixture Filter for Acoustic Source Localization and Tracking

Abstract:
In this work, we address the problem of tracking an acoustic source based on measured time differences of arrival (TDOA). The classical solution to this problem consists in using a detector, which estimates the TDOA for each microphone pair, and then applying a tracking algorithm, which integrates the “measured” TDOAs in time. Such a two-stage approach presumes 1) that TDOAs can reliably be estimated; and 2) that errors in detection behave in a well-defined fashion. The presence of noise and reverberation, however, causes larger errors in the TDOA estimates and, thereby, ultimately lowers the tracking performance. We propose to counteract this effect by considering a multiple hypothesis filter, which propagates the TDOA estimation uncertainty to the tracking stage. That is achieved by considering multiple TDOA estimates and then integrating the resulting TDOA observations in the framework of a Gaussian mixture filter. Experimental results show that the proposed filter has a significantly lower angular error than a multiple hypothesis particle filter. Index Terms — Direction of arrival estimation, Microphone Arrays, Monte Carlo methods, Kalman filters