[Athen] Docsoft

Gaeir Dietrich gdietrich at htctu.net
Thu May 8 16:08:03 PDT 2008

If we had been captioning "for real," then yes, we would have used the
script...particularly since the "voice talent" (me) read exactly from the

What we were attempting to check was how accurate DocSoft would be with
something recorded under ideal studio conditions vs. in the uncontrolled
classroom environment.

What we found was that even under the best recording conditions with clear
sound, precise enunciation, and no "nonsense syllables" (uh, hmmm, etc.),
DocSoft did not come close to being completely accurate.

One other note, a very accurate and quick way to generate a transcript is to
have someone who is a very good Dragon user listen to the recording and
speak it into Dragon. This technique can work very well. It can also be a
great job opportunity for one of your proficient Dragon students.

Good luck!

Gaeir (rhymes with "fire") Dietrich
High Tech Center Training Unit of the
California Community Colleges
De Anza College, Cupertino, CA

-----Original Message-----
From: athen-bounces at athenpro.org [mailto:athen-bounces at athenpro.org] On
Behalf Of James Bailey
Sent: Thursday, May 08, 2008 1:33 PM
To: skeegan at htctu.net; Access Technologists in Higher EducationNetwork
Subject: Re: [Athen] Docsoft

On Thu, 8 May 2008 12:47:17 -0700, "Sean Keegan" <skeegan at htctu.net> wrote:

> Others that were testing the system (for podcasting-type situations) were

able to get similar levels of recognition provided that they scripted

> out what they planned to say before recording.

Hi Sean,

If there's a script why wouldn't you just work from that? I don't mean this
rhetorically, how helpful is a script?


James Bailey
Adaptive Technology Access Adviser, University of Oregon
1299 University of Oregon
Eugene, OR 97403-1299
Office: 541-346-1076
jbailey at uoregon.edu

Athen mailing list
Athen at athenpro.org

More information about the athen-list mailing list