A Bayesian Binaural System for 3D Sound-Source Localisation

C. Pinho (1) , J.F. Ferreira (1) , Pierre Bessière (2) , J. Dias (1)

1 ISR-UC - Institute of Systems and Robotics
2 E-MOTION - Geometry and Probability for Motion and Action

In this text we present a Bayesian system of auditory localisation in distance, azimuth and elevation using binaural cues only.We describe its supporting sensor model and calibration procedure. The binaural system is also integrated in a spatial representation framework for multimodal perception of 3D structure and motion — the Bayesian Volumetric Map (BVM). This solution will enable the implementation of an active perception system with great potential in applications as diverse as social robots or even robotic navigation.

Domains: Computer science

C. Pinho, J.F. Ferreira, Pierre Bessière, J. Dias. A Bayesian Binaural System for 3D Sound-Source Localisation. nternational Conference on Cognitive Systems (CogSys 2008), 2008, Karlsruhe, Germany. ⟨hal-00338802⟩