An essential aspect of Auditory Scene Analysis is the localisation of sound sources in relation to theudposition of the listener in the surrounding environment. The human auditory system is capable ofudprecisely locating and separating different sound sources, even in noisy and reverberant environments,udwhereas mimicking this ability by computational means is still a challenging task. In this work, weudinvestigate a Bayesian-network-based approach in the context of binaural sound source localisation.udWe extend existing solutions towards a Bayesian network based blackboard system that includes expertudknowledge inspired by insights into the human auditory system. In order to improve estimationudof source positions and reduce uncertainty caused by front-back ambiguities, hypothesis-driven feedbackudis used. This is accomplished by triggering head movements based on inference results providedudby the Bayesian network. We evaluate the performance of our approach in comparison to existingudsolutions in a sound-source localisation task within a virtual acoustic environment.
展开▼
