Robotic sound-source localisation architecture using cross-correlation and recurrent neural networks

Murray, John C.; Erwin, Harry R.; Wermter, Stefan

Abstract

In this paper we present a sound-source model for localising and tracking an acoustic source of interest along the azimuth plane in acoustically cluttered environments, for a mobile service robot. The model we present is a hybrid architecture using cross-correlation and recurrent neural networks to develop a robotic model accurate and robust enough to perform within an acoustically cluttered environment. This model has been developed with considerations of both processing power and physical robot size, allowing for this model to be deployed on to a wide variety of robotic systems where power consumption and size is a limitation. The development of the system we present has its inspiration taken from the central auditory system (CAS) of the mammalian brain. In this paper we describe experimental results of the proposed model including the experimental methodology for testing sound-source localisation systems. The results of the system are shown in both restricted test environments and in real-world conditions. This paper shows how a hybrid architecture using band pass filtering, cross-correlation and recurrent neural networks can be used to develop a robust, accurate and fast sound-source localisation model for a mobile robot.

Citation

Murray, J. C., Erwin, H. R., & Wermter, S. (2009). Robotic sound-source localisation architecture using cross-correlation and recurrent neural networks. Neural Networks, 22(2), 173-189. https://doi.org/10.1016/j.neunet.2009.01.013

• Journal Article Type: Article
• Online Publication Date: Feb 4, 2009
• Publication Date: Mar 1, 2009
• Deposit Date: Oct 25, 2018
• Journal: Neural Networks
• Print ISSN: 0893-6080
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 22
• Issue: 2
• Pages: 173-189
• DOI: https://doi.org/10.1016/j.neunet.2009.01.013
• Keywords: Robotics; Human–robot interaction; Sound-source localisation; Cross-correlation; Recurrent neural networks
• Public URL: https://hull-repository.worktribe.com/output/799550
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S0893608009000136
• Related Public URLs: http://eprints.lincoln.ac.uk/9703/