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/1842/915

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

Files in This Item:

File Description SizeFormat
Frankel_King_IEEE2006.pdf557.15 kBAdobe PDFView/Open
Frankel_King_IEEE2006.ps1.1 MBPostscriptView/Open
Title: Speech recognition using linear dynamic models.
Authors: Frankel, Joe
King, Simon
Issue Date: 2006
Citation: IEEE Transactions on Speech and Audio Processing, 2006 (In Press)
Publisher: IEEE
Abstract: The majority of automatic speech recognition (ASR) systems rely on hidden Markov models, in which Gaussian mixtures model the output distributions associated with sub-phone states. This approach, whilst successful, models consecutive feature vectors (augmented to include derivative information) as statistically independent. Furthermore, spatial correlations present in speech parameters are frequently ignored through the use of diagonal covariance matrices. This paper continues the work of Digalakis and others who proposed instead a first-order linear state-space model which has the capacity to model underlying dynamics, and furthermore give a model of spatial correlations. This paper examines the assumptions made in applying such a model and shows that the addition of a hidden dynamic state leads to increases in accuracy over otherwise equivalent static models. We also propose a time-asynchronous decoding strategy suited to recognition with segment models. We describe implementation of decoding for linear dynamic models and present TIMIT phone recognition results.
Keywords: automatic speech recognition
Markov models
speech
TIMIT
URI: http://hdl.handle.net/1842/915
Appears in Collections:CSTR publications
Linguistics and English Language 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