Connectionist models of categorical perception of speech

Author

Damper, R.I.

Author_Institution

Dept. of Electron. & Comput. Sci., Southampton Univ., UK

fYear

1994

fDate

13-16 Apr 1994

Firstpage

101

Abstract

Responses of both human and animal listeners to synthetic stop-consonant/vowel stimuli in which voice onset time (VOT) is uniformly varied are known to be `categorical´ but an explanation of this phenomenon remains elusive. A `composite´ model consisting of a physiologically-realistic auditory model feeding its patterns of neural firing to an artificial neural network is shown to reproduce listeners´ behaviour in classical categorical-perception (CP) studies. However, whether the model also reproduces the so-called boundary-shift phenomenon apparently depends upon precise details of the auditory model and so, by implication, upon peripheral auditory processing

Keywords

feedforward neural nets; hearing; speech intelligibility; animal listeners; artificial neural network; auditory model; boundary-shift phenomenon; categorical perception; classical categorical-perception; composite model; human listeners; neural firing; peripheral auditory processing; physiologically-realistic auditory model; speech; synthetic stop-consonant stimuli; synthetic vowel stimuli; voice onset time; Animals; Artificial neural networks; Biological system modeling; Computer networks; Computer science; Humans; Labeling; Signal processing; Speech processing; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on

Print_ISBN

0-7803-1865-X

Type

conf

DOI

10.1109/SIPNN.1994.344955

Filename

344955