Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >

Please use this identifier to cite or link to this item:

View Statistics

Files in This Item:

File Description SizeFormat
Rohwer ICASSP.pdf234.91 kBAdobe PDFView/Open
Title: Unstable connectionist networks in speech recognition
Authors: Rohwer, Richard
Renals, Steve
Terry, Mark
Issue Date: Apr-1988
Citation: Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on, 11-14 April 1988 Page(s):426 - 428 vol.1
Publisher: IEEE
Abstract: Connectionist networks evolve in time according to a prescribed rule. Typically, they are designed to be stable so that their temporal activity ceases after a short transient period. However, meaningful patterns in speech have a temporal component: therefore it seems natural to attempt to map the temporality of speech patterns onto the temporality of an unstable network. The authors have begun some exploratory experiments to train networks to recognise temporal patterns. They have designed fully connected networks that are trained to emulate and classify sequences by regarding each temporal state of a network as a layer in a feedforward network. Training is then performed by a variant of the back-propagation algorithm. They have conducted initial experiments using the output of a peripheral auditory model.
ISSN: 1520-6149
Appears in Collections:CSTR publications

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy