Robust Self-Localization of Microphone Arrays Using a Minimum Number of Acoustic Sources
Matthias Schrammen, Ahmad M. Hamad, Peter Jax · 2019
Multi-microphone signal processing is becoming increasingly popular in applications such as distant speech recognition or communication in adverse environments. To deploy source localization or signal enhancement algorithms like beamforming the locations of the microphones must be known. One well-studied approach to retrieve the relative positions of the microphones is based on time-difference-of-arrival (TDoA) measurements. However, current approaches are restricted to scenarios with a large number of sources or specific coherence assumptions. In this paper a non-iterative approach based on orthogonal geometric projection (OGP), which is able to perform a blind self-localization of the array in 2D with only two sources at arbitrary positions, is presented and extended to estimate a 3D array shape with only three sources. Furthermore, an efficient method for outlier correction in the pairwise distance (PD) estimates is proposed, that significantly reduces the position error.