Optimal Microphone Placement for Localizing Tonal Sound Sources

This work is concerned with determining optimal microphone placements that allow for an accurate location estimate of the sound sources, taking into account the expected signal structure of voiced speech, as well as the expected location areas and the typical range of the fundamental frequencies of the speakers. To determine preferable microphone placements, we propose a scheme that minimizes a theoretical lower bound on the variance of the location estimates over the possible sensor placements, while taking into account the expected variability in the impinging signals. Numerical examples and real measurements illustrate the performance of the proposed scheme.