TU Dortmund Department of Computer Science LS XII Pattern Recognition GroupPublications → Publication Details

Online Multi-Speaker Tracking Using Multiple Microphone Arrays Informed by Auditory Scene Analysis

Axel Plinge and Gernot A. Fink
European Signal Processing Conference (EUSIPCO), Marrakesh, Morocco, 2013.

Tracking multiple speakers by microphone arrays is used for practical applications such as video conferencing. An important task is the integration of multiple arrays with correct association of multiple concurrent speakers. A single-array tracking approach based on CASA is extended here to probabilistic tracking with multiple arrays to handle a varying number of moving speakers over time and instantaneously assign the concurrent localizations of multiple sensors to the speakers. Tracking is done simultaneously in angular and Euclidean space. By evaluation on the publicly available AV16.3 corpus, the effectiveness of the method is shown with recordings of real speakers in a reverberant conference room.

 [bib] [pdf]