Newsgroups: comp.speech
Path: cantaloupe.srv.cs.cmu.edu!das-news.harvard.edu!news2.near.net!MathWorks.Com!europa.eng.gtefsd.com!howland.reston.ans.net!EU.net!ieunet!curia!csws4.ucc.ie!turlough
From: turlough@odyssey.ucc.ie (Turlough FitzPatrick)
Subject: HMM and speech recognition
Message-ID: <CwFr8G.36C@curia.ucc.ie>
Sender: usenet@curia.ucc.ie
Reply-To: turlough@odyssey.ucc.ie
Organization: Computer Science Dept., University College, Cork, Ireland
References: <CwFE2J.tG@aisb.ed.ac.uk>
Date: Tue, 20 Sep 1994 16:02:39 GMT
Lines: 13


Hi out there,
I am currently trying to stick together a speech recognition
system using neural networks. I have seen a lot of references
to hidden markov maps in this area and would like to see
how they compare to neural nets, better or worse. I would 
especially be interested in any research/results using the
TIMIT speech data base. As I am going to use it for 
comparison all the statistics possible are welcome. 
I would welcome any info, be it actual data, discussion or site
references etc., anything at all.
Thanks a lot,
turlough.
