Hello folks,
I am also a new member of this list. My name is David Garbose and I
work with Newspeak Communications in (the currently very snowy) Vermont.
I have been a speech therapist for 15 years and have been selling
equipment and training people in the use of speech recognition software
for six years.
I think that you point out one of the more important aspects of speech
recognition. Many people who exhibit reduced intelligibility in their
general speech patterns can make significant improvements by using
speech recognition technology.
One of the greatest inhibitions to improving speech (or any problem,
really) is the failure to admit that you are having a problem. One of
the more difficult assignments of the speech therapist is to convince
the client that they are actually having a problem. Many people choose
to blame the listener for not understanding them. As a result they do
not attempt to change their speech patterns. When you're talking to a
computer you have no one person to blame, and you really shouldn't kick
the computer. If you really want to make the software work appropriately
you have to talk clearer. I have worked with many people who have
significantly improved their articulation as a result of the immediate
feedback from speech recognition software. Certainly the one most
important factor in improving the recognition percentage is clear
speech, no matter what the software is.
I would suggest using a continuous speech recognition software program,
such as Dragon Systems NaturallySpeaking. You need to purchase at least
the preferred edition so that you have the capability of using the audio
playback of the users voice, and the text-to-speech capabilities for
editing documents. The audio playback feature can assist a person to
recognize their own poor speech patterns. "Oh, that is why it did not
understanding me."
Make sure you have enough computer power to run the program.
Recommended system: at least
Pentium III 500
256 megabytes of RAM
512 L2 cache
Tested Sound Card
Minimum system:
Pentium II 333
96 megabytes of RAM
512 L2 cache
Tested Sound Card
David Garbose, MA CCC SLP
Newspeak Communications
dave@newspeakcom.com
spk2wrt@phoenix.edc.org wrote:
>
> My name is Leslie Duffen and I am a new member of the list. I am a
> retired computer studies teacher but my interest is largely personal. I
> have a daughter called Sarah who has Down syndrome but who has done
> remarkably well in spite of this congenital disadvantage. For example
> she reads and speaks well, can drive a car safely at speeds frightening
> to a passenger and can ski, water-ski, etc., etc. Sometimes her speech
> is hard to understand but she does not always accept this. A year or so
> ago I started using speech recognition with her in an attempt to
> persuade her that it was sometimes her fault if people could not
> understand her. We used IBM Voice Type Via Voice. I hoped to improve her
> articulation and this was fairly successful but practice always followed
> the same pattern. There was initial success and then the programme
> started producing rubbish. After a few months of this we gave up in
> despair. Nevertheless I am still convinced that speech recognition has a
> lot to offer in improving articulation for people such as Sarah and,
> perhaps, as the basis of a programme for teaching reading based on word
> recognition.
> Any comments would be gratefully received.
> Leslie Duffen
>
____________________________________________________________
To post a message to the spk2wrt list, send your message to:
spk2wrt@mail.edc.org. To reply to a message, simply use the reply button in
your email program (do not change the subject line in any way). To access the
spk2wrt archive containing a full list of all discussion threads to date, point
your Web browser to: http://www.edc.org/spk2wrt/hypermail/. For questions about
this list, please send a message to: spk2wrt@edc.org. For more information
about the Speaking to Write project, please visit our Web site at:
http://www.edc.org/spk2wrt
This archive was generated by hypermail 2b29 : Tue Feb 22 2000 - 16:02:34 EST