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/1842/1215

This item has been viewed 52 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Williams_Renals_eurosp97-conf.pdf54.17 kBAdobe PDFView/Open
Williams_Renals_eurosp97-conf.ps35.15 kBPostscriptView/Open
Title: Confidence measures for hybrid HMM/ANN speech recognition.
Authors: Williams, Gethin
Renals, Steve
Issue Date: 1997
Citation: In Proc. Eurospeech, pages 1955-1958, Rhodes, 1997.
Publisher: International Speech Communication Association
Abstract: In this paper we introduce four acoustic confidence measures which are derived from the output of a hybrid HMM/ANN large vocabulary continuous speech recognition system. These confidence measures, based on local posterior probability estimates computed by an ANN, are evaluated at both phone and word levels, using the North American Business News corpus.
URI: http://hdl.handle.net/1842/1215
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