Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!warwick!uknet!mcsun!uunet!think.com!spool.mu.edu!howland.reston.ans.net!sol.ctr.columbia.edu!news.cs.columbia.edu!beshers
From: beshers@cs.columbia.edu (Clifford Beshers)
Subject: Re: Verbex Listen for Windows
In-Reply-To: mwong@rad.verbex.com's message of Thu, 24 Jun 1993 19:44:11 GMT
Message-ID: <BESHERS.93Jun25085614@tune.cs.columbia.edu>
Sender: news@cs.columbia.edu (The Daily News)
Organization: Columbia University Computer Science
References: <16BE7102FA.HOTTODDY@VM.TEMPLE.EDU> <C8DqM0.8zs@dircon.co.uk>
	<C8w7II.9Ky@murdoch.acc.Virginia.EDU>References:
	<1993Jun24.194411.16746@rad.verbex.com>
Date: Fri, 25 Jun 1993 13:56:14 GMT
Lines: 39

In article <1993Jun24.194411.16746@rad.verbex.com> mwong@rad.verbex.com (Maurice K. Wong) writes:

   From: mwong@rad.verbex.com (Maurice K. Wong)
   Organization: Verbex Voice Systems, Inc.
   I would like to point out the crucial difference between Verbex's
   "Listen for Windows" and Dragon Dictate: the Verbex system is for
   *continuous speech* recognition, whereas Dragon Dictate is for
   *isolated word* recognition; in other words, for Verbex you can say
   something like "Please open the second editor window" in one breathe
   and in a natural manner, but for Dragon you have to say "Please
   <pause> open <pause> the <pause> second <pause> graphics <pause>
   window".  Of course, the pause between words can be extremely short,
   but it does have to be there.  This distinction between continuous
   speech and isolated word is crucial for some applications and less so
   for others, depending on how and what you want to say to the system.

   Maurice Wong

Let's clarify that.  Verbex is not a dictation system, like
Dragon Dictate.  It supports command and control.  You can say
"Please open the second editor window" in one breath, because it
is trying to recognize that phrase as a whole, rather than trying
to sort out which words.

Verbex is a nice, inexpensive product for controlling windows,
but it does not have nearly the power of DD.  No commercially
available speech recognition systems support full dictation and
continuous speech, that I know of.

--
-----------------------------------------------
Clifford Beshers
450 Computer Science Department
Columbia University
New York, NY 10027
Office:  (212) 939-7060
Fax:     (212) 666-0140
Email:   beshers@cs.columbia.edu

