Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!nntp.club.cc.cmu.edu!hudson.lm.com!news.pop.psu.edu!news.cac.psu.edu!howland.reston.ans.net!news.sprintlink.net!pipex!sunic!news.uni-c.dk!diku!flanhart
From: flanhart@diku.dk (Rene Andersen)
Subject: Whatever happened to TDNN?
Message-ID: <CzMB98.2Do@odin.diku.dk>
Sender: flanhart@tyr.diku.dk
Date: Mon, 21 Nov 1994 12:41:32 GMT
Organization: Department of Computer Science, U of Copenhagen
X-Newsreader: NN version 6.5.0 #12 (NOV)
Keywords: TDNN
Lines: 16

Hi

I did a project with TDNN (Time-Delay Neural Nets) about a year ago
for speech recognition.  The results where quite good. We had no
problems achieving more than 90% recognition of whether a sound is
voiced or unvoiced.  

The TDNN seemed very convincing, but I haven't really heard anything
about it since.  Does anybody know what the state of the art is when
it comes to TDNN?


Best 

Ren'e Andersen (flanhart@diku.dk)

