A fast cumulative Steered Response Power for multiple speaker detection and localization
Youssef Oualil, Friedrich Faubel, Dietrich Klakow · European Signal Processing Conference · 2013
This paper presents a novel approach for detecting and localizing multiple speakers using a microphone array. In this framework, the classical Steered Response Power (SRP) technique is combined with a novel two-step search strategy to reduce the computation cost. The approach taken here performs the localization by 1) using the spatial information provided by each Generalized Cross Correlation (GCC) function to reduce the search space to a few subspaces that are likely to contain a source. From these, the most likely region is extracted as the subspace that maximizes the Cumulative SRP. Then, 2) the optimal source location is estimated using the classical search approach in the reduced space. The noise/speaker detection is further improved using an unsupervised Bayesian classifier. Experiments on the AV16.3 corpus show that the proposed method is approximately 47 times faster than the classical SRP, without any noticeable degradation of the localization performance.