Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!pipex!uknet!cam-eng!mjfg
From: mjfg@eng.cam.ac.uk (M. J. F. Gales)
Subject: Technical Report Available
Sender: mjfg@eng.cam.ac.uk (Mark Gales)
Message-ID: <1993Jul9.161619.18717@eng.cam.ac.uk>
Date: Fri, 9 Jul 1993 16:16:19 GMT
Nntp-Posting-Host: dsl.eng.cam.ac.uk
Organization: Cambridge University Engineering Department, UK
Lines: 64

The following technical report is available by anonymous ftp from the
archive of the Speech, Vision and Robotics Group at the Cambridge
University Engineering Department.

                   PARALLEL MODEL COMBINATION FOR
        	    SPEECH RECOGNITION IN NOISE

		    Mark Gales and Steve Young

                Technical Report CUED/F-INFENG/TR135

	    Cambridge University Engineering Department 
		        Trumpington Street 
		        Cambridge CB2 1PZ 
			     England 


                             Abstract

This report addresses the problem of automatic speech recognition in
the presence of interfering noise. The approach adopted is to
compensate the parameters of a clean speech model given the statistics
of the interfering noise. In this work these statistics are assumed to
be modelled by a Hidden Markov Model (HMM). The basic theory of static
coefficient Parallel Model Combination (PMC) is reviewed and placed
within the framework of approximating the Maximum Likelihood (ML)
estimate of the corrupted speech model, given the clean speech and
interfering noise models. In addition the paper examines the problem
of compensating delta coefficients in a PMC framework. Expressions for
ML estimates of delta coefficients are derived and computationally
efficient approximations of these estimates are given. The
effectiveness of compensating delta parameters is discussed.

Keywords: speech recognition, noise compensation, HMM, PMC.

************************ How to obtain a copy ************************

a) Via FTP:

unix> ftp svr-ftp.eng.cam.ac.uk
Name: anonymous
Password: (type your email address)
ftp> cd reports
ftp> binary
ftp> get gales_tr135.ps.Z
ftp> quit
unix> uncompress gales_tr135.ps.Z
unix> lpr gales_tr135.ps (or however you print PostScript)

b) Via postal mail:

Request a hardcopy from

Mark Gales,
Cambridge University Engineering Department, 
Trumpington Street, 
Cambridge CB2 1PZ,
England.

or email me: mjfg@eng.cam.ac.uk




