Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!MathWorks.Com!europa.eng.gtefsd.com!howland.reston.ans.net!pipex!sunic!news.uni-c.dk!diku!tyr.diku.dk!flanhart
From: flanhart@diku.dk (Rene Andersen)
Subject: Re: Neural Nets & Speech, basic help needed.
Message-ID: <flanhart.782054639@tyr.diku.dk>
Sender: flanhart@tyr.diku.dk
Date: Thu, 13 Oct 1994 13:23:59 GMT
References: <37hbik$o16@m1.cs.man.ac.uk>
Organization: Department of Computer Science, U of Copenhagen
Lines: 20

For speech recognition using neural net try having a look at so-called
Time-Delayed Neural Nets (TDNN).  Basic articles are the following:


Alexander Waibel, Toshiyuki Hanazawa, Geoffrey Hinton,
Kiyohiro Shikano \& Kevin J.\ Lang: 
        Phoneme recognition using Time-Delay Neural Networks.
        IEEE transactions on acoustics, speech and signal processing. 
        Vol.\ 37, no.\ 3, March 1989. 


Alexander Waibel, Hidefumi Sawai \& Kiyohiro Shikano: 
        Modularity and scaling in large phonemic Neural Networks.
        IEEE transactions on acoustics, speech and signal processing.
        Vol.\ 37, no 12, December 1989.


best

Ren'e Anderses
