A novel biologically inspired neural network solution for robotic 3D sound source sensing

This paper presents a novel real-time robotic binaural sound localization method based on hierarchical fuzzy artificial neural networks and a generic set of head related transfer functions. The robot is a humanoid equipped with the KEMAR artificial head and torso. Inside the ear canals two small microphones play the role of the eardrums in collecting the impinging sound waves. The neural networks are trained using synthesized sound sources placed every 5° from 0° to 255° in azimuth, and every 5° from  − 45° to 80° in elevation. To improve generalization, the training data was corrupted with noise. Thanks to fuzzy logic, the method is able to interpolate at its output, locating with high accuracy sound sources at positions which were not used for training, even in presence of strong distortion. In order to achieve high localization accuracy, two different binaural cues are combined, namely the interaural intensity differences and interaural time differences. As opposed to microphone-array methods, the presented technique, uses only two microphones to localize sound sources in a real-time 3D environment.