Newsgroups: comp.publish.cdrom.multimedia,comp.publish.cdrom.software,comp.speech
Path: cdrom.com!barrnet.net!sgiblab!sdd.hp.com!math.ohio-state.edu!howland.reston.ans.net!agate!library.ucla.edu!news.mic.ucla.edu!ucla-cs!netcon!microme!jraven
From: jraven@microme.uucp (John Raven)
Subject: Re: Speech Recognition Technologies
Message-ID: <1994Jan4.064518.14953@microme.uucp>
Sender: John Raven
Organization: Micro Memory Inc., Chatsworth, Ca.
References: <1994Jan3.180304.5618@netcon.smc.edu>
Date: Tue, 4 Jan 94 06:45:18 GMT
Lines: 15
Xref: cdrom.com comp.publish.cdrom.multimedia:128 comp.publish.cdrom.software:115 comp.speech:156

If you are going to make it software based then the machine becomes
an issue.

What machine will it run on and how much crunch power will it have?

I am intersted in SpeechRecog for professional reasons.

I have found a good system (don't have one but have seen demo)

It takes an extra card, runs on an IBM RS/6000 and costs just 
under five thou. I think that is pretty much what it takes to
get good SR.

Bad or marginal SR is just frustrating.