Show simple item record

dc.contributor.authorRohwer, Richard
dc.contributor.authorRenals, Steve
dc.contributor.authorTerry, Mark
dc.coverage.spatial3en
dc.date.accessioned2006-06-06T10:30:38Z
dc.date.available2006-06-06T10:30:38Z
dc.date.issued1988-04
dc.identifier.citationAcoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on, 11-14 April 1988 Page(s):426 - 428 vol.1en
dc.identifier.issn1520-6149
dc.identifier.otherDOI: 10.1109/ICASSP.1988.196609
dc.identifier.urihttp://ieeexplore.ieee.org/
dc.identifier.urihttp://hdl.handle.net/1842/1206
dc.description.abstractConnectionist 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.en
dc.format.extent240551 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEEen
dc.titleUnstable connectionist networks in speech recognitionen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record