Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!doc.ic.ac.uk!agate!usenet.ins.cwru.edu!magnus.acs.ohio-state.edu!zaphod.mps.ohio-state.edu!sdd.hp.com!cs.utexas.edu!uunet!munnari.oz.au!metro!parlo!andrewh
From: andrewh@ee.su.OZ.AU (Andrew Hunt)
Subject: Phonetic recognition accuracy
Message-ID: <1992Nov26.232721.16234@ucc.su.OZ.AU>
Sender: news@ucc.su.OZ.AU
Nntp-Posting-Host: parlo.ee.su.oz.au
Reply-To: andrewh@e.su.OZ.AU (Andrew Hunt)
Organization: University of Sydney, Australia
Date: Thu, 26 Nov 1992 23:27:21 GMT
Lines: 16


Can anyone provide information on the current best performance of
phonetic/phonemic recognisers?  I am interested in speaker independent
continuous speech recognisers (like on TIMIT).  I am hoping to get brief 
information on the accuracy of the systems and of the technique used.

Are neural-nets, HMMs, hybrids or something else in the lead at the moment?


Thanks in advance,

Andrew Hunt
Speech Technology Research Group		Ph:  61-2-692 4509
Dept. of Electrical Engineering			Fax: 61-2-692 3847
University of Sydney, NSW, 2006, Australia	email: andrewh@ee.su.oz.au

