Self-Localization of Distributed Microphone Arrays Using Directional Statistics with DoA Estimation Reliability
Szymon Woźniak, Konrad Kowalczyk, Máximo Cobos · 2019
This paper addresses the problem of self-localization of distributed microphone arrays from microphone recordings by following a two-step optimization procedure. In the first step, the relative geometry of the sources and arrays is inferred by the proposed maximum likelihood estimator. It is derived under the assumption that the acquired unit-norm vectors pointing towards the unknown source positions follow a von Mises-Fisher distribution in a D-dimensional space. In the second step, the absolute positions and synchronization offsets between the arrays are estimated from the inferred relative geometry by using the Least Squares procedure. To improve the accuracy of the method, we propose as well the use of a reliability measure for the estimated Directions of Arrival based on the presented directional statistics model. The results of numerical experiments confirm the validity of the proposed approach.