Title :
A spherical basis function neural network for pole-zero modeling of head-related transfer functions
Author :
Jenison, Rick L.
Author_Institution :
Dept. of Psychol., Wisconsin Univ., Madison, WI, USA
Abstract :
This paper describes a neural network for approximating the parameters of a pole-zero model of the head-related transfer function (HRTF). The von Mises basis function (VMBF) is described whose response depends on spherical rather than Cartesian input coordinates. The VMBF neural network is ideally suited to the problem of learning a continuous mapping from spherical coordinates to acoustic parameters that specify sound source direction. A method for computing the common poles of a set of HRTFs is also discussed
Keywords :
acoustic signal processing; hearing; neural nets; poles and zeros; transfer functions; VMBF neural network; acoustic parameters; artificial neural networks; continuous mapping; head-related transfer functions; learning; pole-zero modeling; sound source direction; spherical basis function neural network; spherical coordinates; von Mises basis function; Artificial neural networks; Distributed computing; Geophysics; Meteorology; Multidimensional systems; Neural networks; Psychology; Shape; Statistical distributions; Transfer functions;
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics, 1995., IEEE ASSP Workshop on
Conference_Location :
New Paltz, NY
Print_ISBN :
0-7803-3064-1
DOI :
10.1109/ASPAA.1995.482966
