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: http://hdl.handle.net/1842/1084

This item has been viewed 1 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Renals 1996 Signal Processing Letters.pdf326.31 kBAdobe PDFView/Open
Title: Phone deactivation pruning in large vocabulary continuous speech recognition
Authors: Renals, Steve
Issue Date: Jan-1996
Citation: IEEE Signal Processing Letters (1996) 3, 3-6.
Publisher: IEEE Signal Processing Society
Abstract: In this letter, we introduce a new pruning strategy for large vocabulary continuous speech recognition based on direct estimates of local posterior phone probabilities. This approach is well suited to hybrid connectionist/hidden Markov model systems. Experiments on the Wall Street Journal task using a 20000 word vocabulary and a trigram language model have demonstrated that phone deactivation pruning can increase the speed of recognition-time search by up to a factor of 10, with a relative increase in error rate of less than 2%.
URI: http://ieeexplore.ieee.org/xpl/tocresult.jsp?isYear=1996&isnumber=10187&Submit32=Go+To+Issue
http://hdl.handle.net/1842/1084
ISSN: 1070-9908
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