Audio Data Fuzzy Fusion for Source Localization

Abstract

This work addresses the problem of audio source localization in multiple speakers indoor scenarios. Three different direction of arrival (DOA) algorithms are applied to measure the angular position of the primary audio source with respect to a reference microphone, then a fuzzy logic-based method is applied to fuse the crisp measurements. The model-free estimation capability of the fuzzy logic enables to gain a good degree of precision keeping low the computational complexity of the system. This two level audio source localization system approach is robust and reliable because each module operates independently from the other, and the fuzzy logic inferential engine has the capability to evaluate qualitatively the performance of each of the DOA measurement subsystems. © Springer-Verlag Berlin Heidelberg 2013.