Susan-I understand your comment about "limited options for text entry".
You may find that Dragon just doesn't provide enough tolerance for the
variability of their voices. However, if I'm understanding your
question you can enroll a voice file using an empty vocabulary which can
be populated with just those words that you would want the software to
recognize for the giving user.
This is accomplished by creating a new profile and at the bottom of the
first enrollment screen selecting Advanced next to Vocabulary. On the
second option of the Advanced dialog dropped on the menu for Vocabulary
Size and select Empty Dictation.
I would then have several ways of adding words to this empty vocabulary.
Using the Add Single Words or Add Words from Documents in the Accuracy
Center would probably be amongst the easiest.
I'd like to try revisiting the General Training issue however... did you
try having someone read one, two, or three word combinations to the
student and seeing if they couldn't "Drive" the general training module?
I'm by no means a pessimist, but if their voice will not generally set
up the general training at all (and we're not talking about just the
first two screens) you may find that Dragon NaturallySpeaking will prove
cumbersome for them.
There is an unpublished registry hack that can improve the general
training tolerance. I have not tried this, but would be happy to share
it with you off list (edward@ngtvoice.com) if you want to muck around in
the registry.
Yours Sincerely, Edward S. Rosenthal, President and CEO, Next Generation
Technologies, Inc., 20006 Cedar Valley Rd. #101, Lynnwood, Wa. 98036.
EM: edward@ngtvoice.com WWW: www.ngtvoice.com
PH: 425-744-1100 ext. 15 FX: 425-778-5547
This document was generated using Dragon NaturallySpeaking Professional
Solutions 7.2 speech recognition technology (please disregard any
remaining misrecognitions).
-----Original Message-----
From: owner-spk2wrt@phoenix.edc.org
[mailto:owner-spk2wrt@phoenix.edc.org] On Behalf Of
spk2wrt@phoenix.edc.org
Sent: Wednesday, December 10, 2003 4:30 AM
To: spk2wrt@phoenix.edc.org
Subject: DNS 7
[Moderator's note. Susan, it probably depends on their level of
dysarthria,
but DragonDictate (i.e., discrete speech) is a great tool, with proper
setup and support and OS problems notwithstanding, for many people who
could never have used continuous speech. I haven't tried it, but
possibly
others here have had more luck using DNS v7 with this population? Bob]
How does one proceed with training a "limited vocabulary" ? I have two
students who have speech problems (both have cerebral palsy), enough so
that the enrollment process was completed by another person reading.
Both of these students need to explore using voice recognition because
of their limited options for text entry. Would the student train one
word at a time within the Accuracy menu? Does anyone have other
suggestions for developing a reasonable voice file? Both students are
mostly dictating a single word at a time at this point - would they do
better with Dragon Dictate, even though I realize there would be
problems when the OS is upgraded to XP?
Thanks in advance! Susan Strejc
____________________________________________________________
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
____________________________________________________________
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 2.1.2 : Wed Dec 17 2003 - 12:28:59 EST