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 31 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Robinson ICASSP.pdf350.85 kBAdobe PDFView/Open
Title: IPA: improved phone modelling with recurrent neural networks
Authors: Robinson, Tony
Hochberg, Mike
Renals, Steve
Issue Date: Apr-1994
Citation: Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on, Volume i, 19-22 April 1994 Page(s):I/37 - I/40.
Publisher: IEEE
Abstract: This paper describes phone modelling improvements to the hybrid connectionist-hidden Markov model speech recognition system developed at Cambridge University. These improvements are applied to phone recognition from the TIMIT task and word recognition from the Wall Street Journal (WSJ) task. A recurrent net is used to map acoustic vectors to posterior probabilities of phone classes. The maximum likelihood phone or word string is then extracted using Markov models. The paper describes three improvements: connectionist model merging; explicit presentation of acoustic context; and improved duration modelling. The first is shown to provide a significant improvement in the TIMIT phone recognition rate and all three provide an improvement in the WSJ word recognition rate.
ISSN: 1520-6149
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