12.1647, Sum: Speech/Text Program - Correction

[The LINGUIST Network]

LINGUIST List:  Vol-12-1647. Fri Jun 22 2001. ISSN: 1068-4875.

Subject: 12.1647, Sum: Speech/Text Program - Correction

Moderators: Anthony Aristar, Wayne State U.<aristar at linguistlist.org>
            Helen Dry, Eastern Michigan U. <hdry at linguistlist.org>
            Andrew Carnie, U. of Arizona <carnie at linguistlist.org>

Reviews (reviews at linguistlist.org):
	Simin Karimi, U. of Arizona
	Terence Langendoen, U. of Arizona

Editors (linguist at linguistlist.org):
	Karen Milligan, WSU 		Naomi Ogasawara, EMU
	Lydia Grebenyova, EMU		Jody Huellmantel, WSU
	James Yuells, WSU		Michael Appleby, EMU
	Marie Klopfenstein, WSU		Ljuba Veselinova, Stockholm U.
	Heather Taylor-Loring, EMU	Dina Kapetangianni, EMU

Software: John Remmers, E. Michigan U. <remmers at emunix.emich.edu>
          Gayathri Sriram, E. Michigan U. <gayatri at linguistlist.org>

Home Page:  http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, Wayne
State University, and donations from subscribers and publishers.



Editor for this issue: Marie Klopfenstein <marie at linguistlist.org>

=================================Directory=================================

1)
Date:  Thu, 21 Jun 2001 09:55:12 -0400
From:  Annie Clark Ferreira <aclark at lyrix.com>
Subject:  sum: 12.1630 (speech to text)

-------------------------------- Message 1 -------------------------------

Date:  Thu, 21 Jun 2001 09:55:12 -0400
From:  Annie Clark Ferreira <aclark at lyrix.com>
Subject:  sum: 12.1630 (speech to text)

I must apologize to other listers, I deleted the responses I received
regarding this question. I have been asked to post a summary, so here goes:
I actually only received mail from 2 or 3 people regarding this posting.
Kurt Godden was one; he initially suggested Nuance, then IBM ViaVoice,
before realizing that what I was looking for was a program that could
convert voicemail to text, that would need to be speaker-independant, and
not grammar-based.

I also heard from some one at L&H, I'm afraid I can't remember her name.
She suggested I contact someone at L&H Belgium, but again their products
require extensive speaker training.

Mr. Godden referred me to the Turing Test, and he was right.

I also received this note from Randy Harris:

If you meant commercially available tailor-made software (I didn't see your
initial post), I think it's true that there is none. But I have a colleague
who sends me e-mails that he first composes with IBM's viavoice, and there
are other dictation packages out there that could be so modified. And there
is a lot of research into voice-interfaces for e-mail systems, going back
at least to the mid-90s. (Nicole Yankelovich, at Sun Microsystems, has a
few interesting papers on a system called SpeechAct that you can access
from her page (I don't have the URL handy, but I don't imagine there are
too many Yankelovichs at Sun working on voice, so an engine should get you
to her site pretty quickly).

Perhaps the others who responded can repost their responses? Again, I
apologize for not saving those emails and for forgetting your names!!

Annie L. Clark Ferreira
Linguistics Specialist
Lyrix
www.lyrix.com
aclark at lyrix.com

---------------------------------------------------------------------------
LINGUIST List: Vol-12-1647