Skip to Main Content
A novel neural network model for percepting sound direction has been proposed. Our perception model is based on the physiological auditory nervous system in human brain. The model is divided roughly into three sections: preprocessing for input signals; transforming continuous signals to pulse trains; and extracting of features. The last section are implemented using pulse neuron model. A computer simulation has demonstrated that time and level differences between two random signals has been successfully extracted by the model.
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on (Volume:1 )
Date of Conference: 25-29 Oct. 1993