Neural network model of binaural hearing based on spatial feature extraction of the head related transfer function

Author

Wu, Zhenyang ; Weng, Tao ; Wang, Weibin ; Lo, T.F. ; Chan, H.Y. ; Lam, F.K.

Author_Institution

Dept. of Radio Eng., Southeast Univ., Nanjing, China

Volume

3

fYear

1998

fDate

29 Oct-1 Nov 1998

Firstpage

1109

Abstract

In spatial hearing, complex valued head-related transfer function (HRTF) can be represented as a real valued head-related impulse response (HRIR). Using Karhunen-Loeve expansion, the spatial features of the normalized HRIRs on measurement space can be extracted as spatial character functions. A neural network model based on Von-Mises function is used to approximate the discrete spatial character function of HRIR. As a result, a time-domain binaural model is established and it fits the measured HRIRs well

Keywords

backpropagation; feature extraction; hearing; neural nets; physiological models; principal component analysis; transfer functions; transient response; Karhunen-Loeve expansion; Von-Mises function; backpropagation; binaural hearing; discrete spatial character function; head related transfer function; hearing space; inverse filter; neural network model; principal components analysis; real valued head-related impulse response; spatial character functions; spatial feature extraction; spatial hearing; speaker response; time-domain binaural model; virtual auditory space; Auditory system; Ear; Extraterrestrial measurements; Feature extraction; Interpolation; Loudspeakers; Neural networks; Pollution measurement; Principal component analysis; Transfer functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE

Conference_Location

Hong Kong

ISSN

1094-687X

Print_ISBN

0-7803-5164-9

Type

conf

DOI

10.1109/IEMBS.1998.747065

Filename

747065