Exploiting top-down source models to improve binaural localisation of multiple sources in reverberant environments

Relatively few systems for machine hearing exploit top-down information in source localisation, despite there being clear evidence for top-down (e.g., attentional) effects in biological spatial hearing. This paper addresses this issue by proposing a framework for binaural sound localisation that exploits top- down knowledge about the source spectral characteristics in the acoustic scene. Information from source models is used to im- prove the localisation process by selectively weighting binaural cues. The system therefore combines top-down and bottom- up information flow within a single computational framework. Our experiments show that by exploiting source models in this way, sound localisation performance can be improved substan- tially under challenging conditions in which multiple sources and room reverberation are present.