Show simple item record

dc.contributor.authorRenals, Steve
dc.contributor.authorMorgan, Nelson
dc.contributor.authorBourlard, Herve
dc.contributor.authorCohen, Michael
dc.contributor.authorFranco, Horacio
dc.coverage.spatial14en
dc.date.accessioned2006-05-18T14:32:18Z
dc.date.available2006-05-18T14:32:18Z
dc.date.issued1994-01
dc.identifier.citationIEEE Trans. on Speech and Audio Processing (1994) 2, 161-175.en
dc.identifier.issn1063-6676
dc.identifier.uriDigital Object Identifier 10.1109/89.260359
dc.identifier.urihttp://ieeexplore.ieee.org/
dc.identifier.urihttp://hdl.handle.net/1842/1119
dc.description.abstractThe authors are concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system. This is achieved through a statistical interpretation of connectionist networks as probability estimators. They review the basis of HMM speech recognition and point out the possible benefits of incorporating connectionist networks. Issues necessary to the construction of a connectionist HMM recognition system are discussed, including choice of connectionist probability estimator. They describe the performance of such a system using a multilayer perceptron probability estimator evaluated on the speaker-independent DARPA Resource Management database. In conclusion, they show that a connectionist component improves a state-of-the-art HMM system.en
dc.format.extent1693213 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEE Signal Processing Societyen
dc.titleConnectionist probability estimators in HMM speech recognitionen
dc.typeArticleen


Files in this item

This item appears in the following Collection(s)

Show simple item record