A spherical basis function neural network for modeling auditory space

被引:15
作者
Jenison, RL
Fissell, K
机构
[1] Department of Psychology, University of Wisconsin, Madison
关键词
D O I
10.1162/neco.1996.8.1.115
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper describes a neural network for approximation problems on the sphere. The von Mises basis function is introduced, whose activation depends on polar rather than Cartesian input coordinates. The architecture of the von Mises Basis Function (VMBF) neural network is presented along with the corresponding gradient-descent learning rules. The VMBF neural network is used to solve a particular spherical problem of approximating acoustic parameters used to model perceptual auditory space. This model ultimately serves as a signal processing engine to synthesize a virtual auditory environment under headphone listening conditions. Advantages of the VMBF over standard planar Radial Basis Functions (RBFs) are discussed.
引用
收藏
页码:115 / 128
页数:14
相关论文
共 19 条
  • [1] ARNOLD KJ, 1941, THESIS MIT
  • [2] Broomhead D. S., 1988, Complex Systems, V2, P321
  • [3] CHEN JS, 1993, IEEE VIRTUAL REALITY ANNUAL INTERNATIONAL SYMPOSIUM, P188, DOI 10.1109/VRAIS.1993.380779
  • [4] Chiang CH., 1988, Kinematics of spherical mechanisms
  • [5] FISHER NI, 1987, STATISTICAL ANAL SPH
  • [6] Ghil M., 1981, Dynamic Meteorology: Data Assimilation Methods, P139
  • [7] Predicting the Future: Advantages of Semilocal Units
    Hartman, Eric
    Keeler, James D.
    [J]. NEURAL COMPUTATION, 1991, 3 (04) : 566 - 578
  • [8] A MODEL OF HEAD-RELATED TRANSFER-FUNCTIONS BASED ON PRINCIPAL COMPONENTS-ANALYSIS AND MINIMUM-PHASE RECONSTRUCTION
    KISTLER, DJ
    WIGHTMAN, FL
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1992, 91 (03) : 1637 - 1647
  • [9] MARDIA KV, 1972, STATISTICS DIRECTION
  • [10] DIRECTIONAL SENSITIVITY OF SOUND-PRESSURE LEVELS IN THE HUMAN EAR CANAL
    MIDDLEBROOKS, JC
    MAKOUS, JC
    GREEN, DM
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1989, 86 (01) : 89 - 108