Spatial Sound Localization Model Using Neural Network
This work presents the design, implementation and training of a spatial sound localization system for broadband sound in an anechoic environment inspired in the human auditory system and implemented using neural networks. The data acquisition was made experimentally. The model consist in a nonlinear transformer which possesses one module of ITD and ILD extraction and a second module constituted by a neural network that estimates the sound source position in elevation and azimuth angle. A comparison between the model performance using three different bank filters and a sensitivity analysis of the neural network input are also presented. The average error is 2.4º. This project has been supported by the FONDEI fund of Universidad Tecnológica de Chile.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is temporarily free for AES members.