Xref: utzoo comp.windows.misc:907 comp.sys.next:1118 comp.sys.mac:24614 comp.cog-eng:802
Path: utzoo!utgpu!watmath!clyde!att!osu-cis!tut.cis.ohio-state.edu!unmvax!pprg.unm.edu!hc!ames!amdahl!pyramid!leadsv!laic!darin
From: darin@laic.UUCP (Darin Johnson)
Newsgroups: comp.windows.misc,comp.sys.next,comp.sys.mac,comp.cog-eng
Subject: Re: One Step... (long!)
Message-ID: <397@laic.UUCP>
Date: 3 Jan 89 03:34:10 GMT
References: <263@gloom.UUCP> <908@quintus.UUCP> <4524@xenna.Encore.COM> <23040@apple.Apple.COM>
Reply-To: darin@laic.UUCP (Darin Johnson)
Organization: Lockheed AI Center, Menlo Park
Lines: 20

In article <23040@apple.Apple.COM> malcolm@Apple.COM (Malcolm Slaney) writes:
>On the other hand....human like speech recognition has been postulated to
>take on the order of a Tera Flop by the IBM people.  The current problems
>remaining to be solved (other than processor power) are a bunch of front end 
>issues (like noise, multiple speakers speaker adaptation) AND incorporating
>natural language so that homonyms and missing works can be filled in.

This is if you use the standard Von-Neumann architecture, standard
algorithm's etc.  I saw a setup awhile back at UCSD that did speach
recognition using neural networks (P.D.P. for you purists).  Although I
never actually saw it run (only graphics output), it was supposed to be
able to 'decode' sentences in roughly 1/4 real time.  Presumably, this
was with ideal conditions, short sentences, etc.  With a hardware neural
net, real time speach recognition is quite possible with less than a
super-computer.  You wouldn't even have to devote an entire machine room
to it.

-- 
Darin Johnson (leadsv!laic!darin@pyramid.pyramid.com)
	"You can't fight in here! This is the war room.."