EUROSPEECH 2003 - INTERSPEECH 2003
8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003

        

Multi-Array Fusion for Beamforming and Localization of Moving Speakers

Ilyas Potamitis, George Tremoulis, Nikos Fakotakis, George Kokkinakis

University of Patras, Greece

In this work we deal with the fusion of the estimates of independent microphone arrays to produce an improved estimate of the Direction of Arrival (DOA) of one moving speaker, as well as localization coordinates of multiple moving speakers based on Time Delay Of Arrivals (TDOA). Our approach (a) fuses measurements from independent arrays, (b) incorporates kinematic information of speakers' movement by using parallel Kalman filters, and (c) associates observations to specific speakers by using a Probabilistic Data Association (PDA) technique. We demonstrate that a network of arrays combined with statistical fusion techniques provides a consistent and coherent way to reduce uncertainty and ambiguity of measurements. The efficiency of the approach is illustrated on a simulation dealing with beamforming one moving speaker on an extended basis and localization of two closely spaced moving speakers with crossing trajectories.

Full Paper

Bibliographic reference.  Potamitis, Ilyas / Tremoulis, George / Fakotakis, Nikos / Kokkinakis, George (2003): "Multi-array fusion for beamforming and localization of moving speakers", In EUROSPEECH-2003, 1721-1724.