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 5 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Renals 1996.pdf434.28 kBAdobe PDFView/Open
Title: Efficient evaluation of the LVCSR search space using the NOWAY decoder
Authors: Renals, Steve
Hochberg, Mike
Issue Date: May-1996
Citation: Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on, Volume 1, 7-10 May 1996 Page(s):149 - 152.
Publisher: IEEE Signal Processing Society
Abstract: This article further develops and analyses the large vocabulary continuous speech recognition (LVCSR) search strategy reported by Renals and Hochberg (see Proc. ICASSP '95, p.596-9, 1995). In particular, the posterior-based phone deactivation pruning approach has been extended to include phone-dependent thresholds and an improved estimate of the least upper bound on the utterance log-probability has been developed. Analysis of the pruning procedures and of the search's interaction with the language model has also been performed. Experiments were carried out using the ARPA North American Business News task with a 20,000 word vocabulary and a trigram language model. As a result of these improvements and analyses, the computational cost of the recognition process performed by the NOWAY decoder has been substantially reduced.
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