DocumentCode
275955
Title
The application of neural networks to cognitive phonetic modelling
Author
Cawley, G.C. ; Green, A.D.P.
Author_Institution
Essex Univ., Colchester, UK
fYear
1991
fDate
18-20 Nov 1991
Firstpage
280
Lastpage
284
Abstract
A neural network is used to generate control parameters for a parallel formant speech synthesizer, corresponding to a sequence of allophonic tokens. Training is to be accomplished using formant data obtained from both natural and synthetic speech. It is intended that theories of cognitive phonetics, currently being developed in the Department of Language and Linguistics at the University of Essex will be used in order to improve the modelling of coarticulation
Keywords
learning systems; neural nets; speech recognition; speech synthesis; allophonic tokens; coarticulation; cognitive phonetic modelling; neural networks; parallel formant speech synthesizer; training;
fLanguage
English
Publisher
iet
Conference_Titel
Artificial Neural Networks, 1991., Second International Conference on
Conference_Location
Bournemouth
Print_ISBN
0-85296-531-1
Type
conf
Filename
140332
Link To Document