Home /Research /Sound source localisation through active audition
LEARNING

Sound source localisation through active audition

Erik Berglund, Joaquin Sitte

Year
2005
Citations
29

Abstract

This paper presents a novel method for enabling a robot to determine the direction to a sound source through interacting with its environment. The method uses a new neural network, the parameter-less self-organizing map algorithm, and reinforcement learning to achieve rapid and accurate response.

Keywords

Computer scienceSound reinforcement systemSound (geography)Acoustic source localizationReinforcement learningArtificial neural networkRobotSpeech recognitionArtificial intelligenceAcoustics

Related papers

Browse all LEARNING papers