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:

This item has been viewed 63 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Renals IEEE.pdf1.65 MBAdobe PDFView/Open
Title: Connectionist probability estimators in HMM speech recognition
Authors: Renals, Steve
Morgan, Nelson
Bourlard, Herve
Cohen, Michael
Franco, Horacio
Issue Date: Jan-1994
Citation: IEEE Trans. on Speech and Audio Processing (1994) 2, 161-175.
Publisher: IEEE Signal Processing Society
Abstract: The 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.
URI: Digital Object Identifier 10.1109/89.260359
ISSN: 1063-6676
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