AN INTEGRATED FRAMEWORK FORMULTI-CHANNEL MULTI-SOURCE LOCALIZATION AND VOICE ACTIVITY DETECTION

Two of the major challenges in microphone array based adap-tive beamforming, speech enhancement and distant speech recognition, are robust and accurate source localization and voice activity detection. This paper introduces a spatial gra-dient steered response power using the phase transform (SRP-PHAT) method which is capable of localization of competing speakers in overlapping conditions. We further investigate the behavior of the SRP function and characterize theoretically a fixed point in its search space for the diffuse noise field. We call this fixed point the null position in the SRP search space. Building on this evidence, we propose a technique for multi-channel voice activity detection (MVAD) based on detection of a maximum power corresponding to the null position. The gradient SRP-PHAT in tandem with the MVAD form an inte-grated framework of multi-source localization and voice ac-tivity detection. The experiments carried out on real data recordings show that this framework is very effective in prac-tical applications of hands-free communication