To connect to the chat room, go to www.samizdat.com/chat-intro.html
Since the chat itself happens at a rapid pace, it's often difficult to note interesting facts and URLs as they appear live. Here's a place to take a more leisurely look. I've rearranged some of the pieces to try to capture the various threads of discussion (which sometimes get lost in the rush of live chat).
Please send email with your follow-on questions and comments, and suggestions for topics we should focus on in future sessions. So long as the volume of email responses is manageable, I'll post the most pertinent ones here for all to see.
These sessions are hosted by Richard Seltzer. If you would like to receive email reminders of our chat sessions, simply send a blank email message to businessonthewebchats-subscribe@yahoogroups.com or go to http://groups.yahoo.com/group/businessonthewebchats and sign up there.
This is one of the longest-running chat programs on the Web. (Please let us know if you know of ones that are older.) We've been doing this since June 1996.
For transcripts of previous sessions and a list of future topics, www.samizdat.com/chat.html.
For an article on how to make "business chat" work (based on this experience), www.samizdat.com/events.html.
For articles on topics related to this one, check our newsletter, Internet-on-a-Disk www.samizdat.com/ioad.html
11:59 - Richard Seltzer
Hi, Doris. Where are you? What's
your business? What's your
interest in voice recognition?
11:59 - Bob Fleischer
I visited the exhibits at SpeechTEK
2001 in NYC last Friday -- L&H
certainly had one of the more
interesting booths. Of course, then I
read a review that lists all of
L&H's woes.
12:00 - Bob Zwick
I'm an independent consultant
involved in Distance Education. I'm
interested in finding out if voice
to text software can be used to
make a transcript of an Audio
chat session.
12:00 - Richard Seltzer
Bill -- Please introduce yourself
as well, and tell us about your
role at Lernout*Hauspie, and tell
us something about what you have
available now and how people use
your products and where you expect
to take this to in the next stage.
(That's a tall order. Just dive
in with what feels comfortable
as a starting point. Thanks.)
12:00 - Bob Fleischer
I'm particularly interested in
speech on handheld devices (such as
the iPAQ).
12:01 - David
This is David, and Im a consultant,
but am primarily interested in
speech as applied from a server
perspective
12:02 - doris (Re: 11:59 - Richard Seltzer
'Hi, Doris. Where are you?
What's your business? What's your...')
I'm just a student who is interested
in knew technologies. I'd like
to know if the product is Mac
compatible
12:02 - Bill D.
good afternoon Richard, to work
in the product management
organization here at Lernout &
Hauspie, where I oversee
development for all of speech
and language products including the
Dragon NaturallySpeaking product
line.
12:18 - Hibbspc
sorry to be late...breakfast meeting
12:20 - Richard Seltzer
John -- welcome. I'd think that
you'd be very interested in how to
tie voice recognition into telephone-related
apps.
12:02 - Richard Seltzer
Bob -- From the little I've used
Dragon's Naturally Speaking 5, I
suspect that this wouldn't be
good for transcribing an audio chat
session. You train the software
to understand your voice. The more
you train the better it gets.
But it would be very difficult for
the software to deal with multiple
voices in normal conversation.
12:20 - Bob Zwick
Richard - how much training time
(hours) does it take to get accurate
transcriptions ?
12:21 - Richard Seltzer
Bob -- I can't make an accurate
estimate of time at this point.
Need to test and train some more.
Right now, I find it most useful
in a mixed mode -- at least when
composing. I can speak and do
corrections/edits/change-of-minds
manually as I go along, with
keyboard and mouse.
12:20 - Bill D.
Richard, in addition to training
Dragon NaturallySpeaking (which
for native speaker is less than
20 minutes) is also very helpful to
allow the program to scan your
written documents such as Microsoft
Word or some of your sent to e-mail.
By allowing this software to
scan your existing documents it
can extend its vocabulary and
understand your writing style
for how you combine words and phrases
together.
12:22 - Bob Zwick
Bill D. - that is very usefull.
Acuracy can get pretty good if it
memorized my speach habits.
12:22 - Richard Seltzer
Bill -- that's an interesting
twist -- training the system using
your words, rather than someone
else's words; because what matters
isn't just your voice, but also
your writing style and vocabulary.
12:22 - Bill D.
Richard, Dragon NaturallySpeaking
comes in many versions or
"flavors" as we call them :) that
sell at different price points
with different levels of functionality.
The Essentials product you
mention is our entry-level speech
recognizer which is quite good
for dictating into rich-text fields,
like this chat session. E also
sell higher and versions of the
product, which allow it to be
tightly integrated with office
productivity applications such as MS
office or Corel. This will allow
users extended command and control
be able to speech enable all of
those productivity applications.
12:26 - Bill D.
Richard, this notion of training
the system both through training
scripts and allowing a to read
your documents is an excellent
combination. Perhaps the most
frequently overlooked aspect of
training is allowing it to read
old documents. Your writing style
and my writing style do differ
in the speech recognizer will make
accommodations for that as well
as extended its vocabulary for
unique terms and phrases that
you using your business. in version 6
of Dragon NaturallySpeaking we
made major changes to how the
product improves accuracy by creating
what we call an "Accuracy
Center". This accuracy center,
combines all aspects of training,
microphone tuning, and vocabulary
extension.
12:28 - Richard Seltzer
Bill -- what are the system requirements
for all this sophisticated
training? how much disk space
is the data likely to require? I
presume that the voice you speak
in training is automatically
deleted afterward and only the
results are saved. But does that
data take up significant space?
12:30 - Bill D.
Richard, Dragon NaturallySpeaking,
like most speech recognition
products, is a fairly resource
intensive application. The minimum
system requirements for Dragon
NaturallySpeaking are: a Pentium II
processor, and 64 MB of RAM. Dispatch's
requirements can dairy but
a minimum of 110 MB is required
in depending on the extent of your
audiophile capture, this can rise
to close to 300 MB.
12:23 - Richard Seltzer
All -- When you make corrections,
you can also go into a training
mode to teach the software particular
expressions that you use
often -- and how to spell them
(e.g., the name of your company).
The more often you do that, the
better the results. And once
trained, you really can speak
at a normal pace -- which is faster
than I can type.
12:25 - Richard Seltzer
All -- keep in mind that once
you launch Dragon and turn on its
microphone, your voice input becomes
text output in a wide variety
of applications -- whichever you
current have as active. (It seems
to work best with WordPad, but
email and chat, etc. are also
possible.)
12:16 - Richard Seltzer
All -- when you are dictating
into a document, there are a wide
range of commands available, so
you can speak not only text, but
what to do with the text (like
deleting and capitalizing and going
back and selecting -- the full
ranage; if you get into this, you
don't need to type anything. You
can even use voice to launch new
applications, like Internet Explorer.
12:17 - Richard Seltzer
All -- while you can speak commands,
personally, I find the
application much more useful and
efficient if you mix and match.
You can type and speak and click
-- using whatever method is
simplest for what you are doing
-- e.g., speak, then click and type
to make corrections (instead of
doing that by voice).
12:17 - Bill D.
Richard, in addition to the commanding
control you mention, Dragon
NaturallySpeaking can also be
scripted or programmed to perform
automated tasks such as form-filling
applications and working with
structure documents.
P.S. I am dictating this transcription with Dragon NatSpeak
12:31 - Richard Seltzer
Bill -- are you speaking all of
your input? or just occasionally?
To give John Hibbs and others
here a clearer sense of how good the
accuracy can be (given that you
are using a high-end version and
have probably fine-tuned it to
your voice and speak peculiarities).
12:02 - TomHo
I do interviews on video. I'd
like a system I can use to transcribe
the recordings. Do you have something
that would be effective?
12:03 - Bill D.
Tom, currently we do not have
a technology that can transcribe a
video recording as you mentioned.
We do have a technology using
speech recognition that can index
and allow you to search for words
and phrases against multiple videos
or audio streams.
12:05 - Bob Zwick
Richard - I suppose even me reading
the text transcript would be
faster than my typing it :-)
12:07 - Richard Seltzer
Bob Zwick -- That's an interesting
possibility -- but if you already have
a text transcript, why would you
be using voice recognition to
generate text?
12:08 - Bob Zwick
Richard - the text is only part
of the audio chat. I suppose I
could transcribe my audio and
cut and paste the audience text
portions.
12:10 - Richard Seltzer
Bob -- I think that if you try
it, you will find interesting ways
to take advantage of it, but not
necessarily the kinds of things
you are thinking of now. NB --
I got my 5.0 version (Essentials) for under $50
from Broderbund. And it included
a great high-quality microphone. Incredible price.
A significantly better version
(Preferred) now sells for $179.99.
12:12 - Richard Seltzer
As an example of how well voice
recognition can work and a very
useful application, go to www.lhsl.com
(their Web site), under
About, go to their contact information.
And give them a phone call.
One of the first options is to
go to their directory. There you
simple state the name of the person
you want to speak to and the
system rings their line. Very
slick. And the voice that speaks back
at you, repeating the name that
you spoke, sounds natural, not
machine-like.
12:09 - Richard Seltzer
Bill -- I believe that it is difficult
for those who haven't used
voice recognition to understand
both the limitations and the
possibilities. Could you please
describe some business applications
that you know of?
12:13 - Bill D.
Richard, most of the business
applications for speech recognition
have to do with large volumes
of text creation what we call
document creation services. Speech
recognition's main benefit is
productivity: it is faster to
talk than to type.therefore you see
higher volumes of speech recognition
use in legal departments,
government agencies, in various
medical and General business
practices where large amounts
of document creation is done.
12:13 - Bob Zwick
Richard - are you "speaking" the
text we are seeing ?
12:13 - Richard Seltzer
Bob -- I was trying voice input
to this area just before this
session started and ran into a
few problems -- but they were my
problems, not problems with the
software. I suspect that it would
be best (if trying that) to click
Pause before inputting, otherwise
the automatic refresh gets in
the way. I still have to play around and
experiment some more to be able
to speak-input here. Though it does
seem to be possible. Bill -- are
you speaking or typing now? If you
are set up to speak, could you
try that a bit so people get a sense
of what the output would look
like (with some random and inexact
words every now and then).
12:15 - Bob Zwick
Richard - ahh.... automation getting
in the way of automation :)
12:17 - Bob Zwick
Richard - do you see this as the
new way for authors to write their
manuscripts ?
12:18 - Richard Seltzer
Bob -- I'd like to experiment
with this for writing -- fiction and
articles. I need to do some more
training though. The more you
train the app the more accurate
it is and hence the less time you
have to spend making corrections.
Think of this like scanning --
you always need to proofread text
that you've scanned -- only this
is more like dealing with an early
generation scanner when errors
were more common.
12:26 - Richard Seltzer
I see this as a possible godsend
for someone with carpal tunnel
syndrome or arthritis, also for
slow typers, also allowing
handsfree use of the computer
when you have to do many things at
the same time.
12:28 - Richard Seltzer
Bill, can you please tell us about
other creative business uses of this technology?
John -- Transcription is just
one of many possibilities. You can
also set this up to understand
commands, etc.
12:37 - Richard Seltzer
Bill -- the more business applications
you can tell us about the
better. I'm sure there are important
uses out there that I never
dreamt of.
12:50 - Richard Seltzer
Bill -- is there any place at
the L&H Web site with demos or at
least descriptions of a variety
of business applications? Where
should we go to learn more?
12:54 - Richard Seltzer
Bill -- Is there a good place
for people to see/experience demos of
a variety of business apps or
at least read about them?
13:00 - Bill D.
Richard, yes there are several
examples on our web site and I would
also point you to the section
called value added resellers (VAR.).
Many of these folks, have done
all kinds of interesting
applications based on Dragon NaturallySpeaking.
13:00 - Richard Seltzer
Bill -- thanks. I'll have to take
a close look at that VAR section.
Great stuff. Thanks again.
12:03 - Richard Seltzer
Bill -- following up on the question
from Doris -- are your
products PC-only? Or do they work
with Macs as well?
12:04 - Bill D.
Doris, currently all of the Dragon
applications are at its
PC-based. We did not have products
for the Macintosh platform.
12:05 - doris (Re: 12:04 - Bill D. 'Doris,
currently all of the
Dragon applications are at its...')
Thank you, that effectively eliminates
me
12:03 - Bob Zwick
Richard - I wonder just how bad
multiple voices would be.
12:04 - Richard Seltzer
Bob Zwick -- I think you'd have
to experiment to know for sure. But I
wouldn't have very high hopes.
On the other hand, this could be
very good for transcribing any
voice that is a single voice, if the
speaker had previously "trained"
the software.
12:03 - Bob Fleischer
I believe L&H has products
that are speaker independent and
intended for converting large
volumes of audio to text, right?
12:06 - Bill D.
Bob F., Lernout & Hauspie
does not currently sell a product that is
speaker independant which would
allow you to transcribe large
volumes of audio and text. In
our research labs we are working on
just this problem and it's a derivative
of a large vocabulary
speaker engine like Dragon.
12:07 - TomHo (Re: 12:03 - Bill D. 'Tom, currently
we do not have a
technology that can...')
Bill, What is the name of the
software you mentioned?
12:08 - Ray Dee (Re: 12:07 - TomHo 'Bill, What
is the name of the
software you mentioned?...')
Tom Ho -- Do you know of a similar
system?
12:08 - Bill D.
Tom H. The product used to indexed
Digital media is called
MediaIndexer we shipped our first
version of this product in July
of 2001.
2:25 - Hibbspc
I was thinking that Dragon was
more like the text you see on t.v.
where the voices are transcribed
"on the fly" for the hearing
impaired. Is that part of what
your company offers?
12:28 - Hibbspc
I was hopeful to see "it" this
way - during events, have the
software "listen" to the speakers
for automatic, instant text
traslations which were (either
or both) uploaded in the original
language and/or machine translated
into other languages. No?
12:28 - Bob Zwick
BillD. - does Rush Limbaugh use
you product to see what his radio
callin people are saying ?
12:28 - Bill D.
Hibbspc, No, the Teleprompter
unit to see on television is
typically done manually by human
beings. Naturally speech
recognition is being looked at
to augment this process and allow it
to fully transcribed feature like
broadcasts.Currently, there are
some research challenges we have
to overcome, such as music
overlays with spoken text: which
really confuse the speech
recognizers today.
12:31 - Hibbspc
Is the bottom line, at least for
now that each individual speaker
has to "train" the software, otherwise
the text is hopelessly
inaccurate?
12:33 - Richard Seltzer
John Hibbs -- Yes, I'd say that
the training is absolutely
essential, at least at today's
level of development. What's your
take on that, Bill?
12:34 - Bill D.
Hibbspc, large vocabulary recognition
products, like Dragon
NaturallySpeaking, do require
training. The notion of speaker
independent recognition, is probably
several years away. We work
extensively here in our research
department on just this problem
and have reasonable accuracy for
certain applications but we are
not prepared to make this commercially
available today.
12:39 - Hibbspc
As I understand it, we could not
take our audio archives and run
thrm through Dragon and expect
to have a reasonably accurate
transcription of the dialogue?
n our case, the audio was capture d over the telephone and
"delivered" directly to the p.c.
where it (remains) stored. That
audio would not be transcribealbe
- not that I am sure anyone wants
it!
12:41 - Richard Seltzer
John -- I think that the main
consideration would be whether there
was one voice or multiple voices.
If one voice, then it's possible.
But the more different voices,
the lower the accuracy, quickly
deteriorating to useless. Is that
accurate, Bill?
12:40 - Bill D.
Hibbspc, yes, search for a product
called PowerScribe.
12:41 - Hibbspc
thanks re jpowerscribe
12:34 - Bob Zwick
What about the high end product
mentioned earlier. The
one that is used for mass transcription?
Bill can you tell us a little
more about that product?
12:42 - Bill D.
Richard, multi-voice transcription
is still a ways off (probably
two to three years) what we can
do today, is index a multi-voice
audio file. With the product I
mentioned earlier, MediaIndexer
12:43 - Richard Seltzer
Bill -- Are you working with any
of the Web search sites or
producers of search software to
make it possible to index voice
content and therefore make it
searchable? e.g., are you working
with AltaVista?
12:46 - Bill D.
Richard, yes, we have spoken with
various Web content sites who
have digital audio content that
would like it to be indexed and
made searchable. we also talking
with various General business, and
universities, who may have training
video content.
12:47 - Richard Seltzer
Bill -- You might also want to
check with the folks at Vanderbilt
U. who have an archive of all
the network news shows on television
from back in the days of the Viet
Nam War. Indexing the voice of an
archive like that could be very
useful. Also indexing the many
audio files stored by the Library
of Congress.
12:05 - Richard Seltzer
Bill -- if the individual who
recorded the voice also had
previously "trained" the software
to his/her voice, wouldn't that
kind of transcription be possible?
12:29 - Hibbspc
Where can I see this work in a
real live demonstration. You
mentioned Rush Limbaugh - does
he use it some way?
12:29 - Richard Seltzer
Bob -- I strongly doubt that Rush
could use this that way. It's the
same problem -- a random caller
wouldn't have had a chance to train
the system, hence the accuracy
of the recognition would be
frustratingly low. Is that right,
Bill?
12:30 - Hibbspc
re: 12.28 thanks..that helps.
Bill was H&L working on that before
the big money problems?
12::32 - Bill D.
Bob Z. I am not aware that Rush
Limbaugh uses Dragon
NaturallySpeaking. however given
his current condition it may be of
some use.However, telephone recognition
is not merely as accurate
as that through direct microphone
imput.
12:40 - Bob Zwick
Does the input to DragonSpeak
have to be a mic ? Can input be
redirected from software ie. Real
Audio, or audio file players.
12:42 - Richard Seltzer
Bill -- yes, I'm curious too.
Is there a way (with your consumer
products) of feeding a different
audio source (other than a mic)
into the voice recognition software.
12:44 - Bill D.
Richard, in addition to correct
microphone transcription (like I'm
doing right now) Dragon NaturallySpeaking
can transcribe recorded
audio file such as WAV files.
these WAV. files will have to be
recorded by someone who is trained
on the system i.e. someone that
went through Dragon training.That
would be the extent of its
abilities today.
12:46 - Richard Seltzer
Bill -- Does it have to be WAV
files? Those can easily be enormous
-- aobut ten times the size of
MP3. Would MP3 files work?
12:49 - Bill D.
Richard, yes even though they
are large, WAV files are currently
the only format that we support:
no MP3.
12:45 - Richard Seltzer
Bill -- as an interim measure,
if a limited number of people are
typically involved in voice conversations
that need to be
transcribed, is it possible for
each member of that small group to
train the software to their voices
and styles, and then for the
system to recognize the speaker
and adjust automatically, or for
the speakers to start what they
say with their name as a way of
shifting the software to their
profile? Do you have anything like
that now? or are you working on
it?
12:46 - Bob Zwick
Richard - that would be an interesting
experiment. I could train
your software for my voice from
an audio chat room.
12:48 - Richard Seltzer
Bob -- yes, that would be an interesting
experiment. But we'd want
the software to be able to switch
from looking for one speaker
profile to another as speakers
changed in the course of a
conversation.
12:47 - Bill D.
Richard, just clarify the abilities
of Dragon NaturallySpeaking; it
currently cannot do multi-voice
transcriptions, even if they are
trained voices. We do not have
the ability to extract separate
voice profiles from 1 audio stream.
12:49 - Bob Zwick
Bill D. - I understand that (no
multi-voice), but can a system have
multiple personallities that can
be activated ?
12:49 - Richard Seltzer
Bill -- Understood that what I'm
speculating about now isn't
current possible. But shouldn't
it be possible to add a voice
command to your command file that
would change speaker profiles? So
a new speaker could give that
command and hence be understood?
Feels like a short-term development
project that could be useful.
12:50 - Bill D.
Bob, yes Dragon NaturallySpeaking
can support many voice profiles
with one piece of software. Typically
it is licensed to one
individual who may have several
voice files recorded for different
types of microphones, environments
where they may record, or for
mobile recording.
12:51 - Richard Seltzer
Bill, I think that what Bob was
looking for (me too), was a way to
shift from one profile to another,
on the fly.
12:52 - Bob Zwick
Bill D. - that's great. Can mutiple
instances of the program be
running on a system too?
12:32 - Richard Seltzer
Bill -- how long have you been
working in the voice recognition
field? I remember Solzenitsyn's
First Circle and what it had to say
about voice prints. Also, Gordon
Bell, who was Digital's computer
guru back in the 1970s and early
80s began his computing career
focusing on voice recognition,
but got out of it when he realized
how very very difficult it was
to do it well.
12:52 - Richard Seltzer
Bill -- Thinking again of First
Circle by Solzhenitsy, does the
training with Dragon generate
some kind of a voice print? Could
well-trained dragon software be
used determine that a speaker was
in fact who he/she said he/she
was?
12:54 - Bill D.
Richard, the "voiceprint" you
mention is something we refer to in
the industry as speaker verification:
an example of biometric
technology. This is separate and
distinct from Dragon
NaturallySpeaking and we sell
technologies in the speaker
verification space to be used
for identifying users for security
purposes..
12:54 - Bob Fleischer
There are a number of vendors
who sell the terchnology and service
for voice authentication -- DNS
may not be the tool for it, but it
does exist.
12:56 - Richard Seltzer
Bill -- I'd think that that speaker
verification software could be
combined with your Naturally Speaking
to recognize when speakers
change in multi-speaker situations
-- but that's probably years in
the future...
12:57 - Richard Seltzer
Bob Fleischer -- in a short while
we'll be identifiable in so many
ways it's ridiculous (DNA too).
I bet it would be possible to
profile someone based on their
typing style and the vocabulary they
use in typing, so you could know
that the person who is in the chat
room is in fact the person he/she
says...
2:34 - Hibbspc
ah, the "telephone recognition"
area was where my talks centered
about 24 months ago..I guess that
has not moved forward very
much...understandable as I would
think very low demand for same.
12:37 - Bill D.
Hibbspc: actually, telephone recognition
has made great strides the
last several years. We in fact
have developed a product
specifically for medical transcription.
It is sold through a
special distribution channel to
the medical profession. It allows
for telephone based transcription
of medical analysis.the problem
of telephone based recognition
becomes very manageable if you can
limit what is called the domain
i.e if I know what you are going to
talk about my degree of accuracy
will improve dramatically.
12:38 - Hibbspc
Bill, that product you talked
about for the medical industry..is
that on your web site?
12:38 - Richard Seltzer
Bill -- in that medical transcription
application, do you mean that
if you limit the vocabulary --
the allowed words -- then the need
to train to a particular voice
goes down considerably?
12:39 - Bill D.
Richard, mobile transcription,
for instance capturing recordings on
digital audio is best done with
a high-quality machine to begin
with. There is no need to send
the audio file through a microphone
for transcription if it's captured
at first high-quality manner it
can be transcribed directly against
the speech recognizer without
going through microphone imput.
12:40 - Richard Seltzer
Bill -- aside from the medical,
do you have other examples of
multi-voice but limited vocabulary
applications? (perhaps the voice
recognition built into the phone
system at L&H is an example like
that).
12:06 - Richard Seltzer
Bill -- I understand that your
consumer products, like the one I
purchased, are now sold by Broderbund.
Do you still handle the
development of the whole Dragon
line -- including consumer?
12:07 - Bob Zwick
Can you point us to where we can find
out more about L&H ?
12:07 - Bill D.
Richard, all development of Dragon
products are done here at
Lernout & Hauspie; the Broderbund
relationship you mentioned is
purely a retail distributor relationship.
12:08 - Bob Fleischer
www.lhsl.com is mentioned in the
literature I got at SpeechTEK
12:20 - Hibbspc
What was the impact of L&H
going under due to the problems in
Europe with the buy out? are you
now completely independent?
operating out of bankruptcy?
12:08 - Richard Seltzer
Bill -- I understand that you
just came out with a new version of
Naturally Speaking -- 6.0. How
does that differ from 5.0? Is it
just a matter of improved quality
of voice recognition? Or are
there functions you can perform
with it that you couldn't with 5.0?
12:11 - Bill D.
Richard, the new version of Dragon
NaturallySpeaking, version
6.will be available later this
month. As with all new versions of
speech recognition it does have
significant accuracy improvements
and new features such as "Nothing
but Speech" which allows speech
recognizer to ignore extraneous
sounds like "ahhs" and "Umms" that
we all do what I natural conversation.
12:19 - Richard Seltzer
Bill -- Excellent. How does Dragon
NatSpeak differ from the
bare-bones, consumer software
(Naturally Speaking 5.0, Essentials)
that I'm using?
12:11 - Bob Fleischer
I also noticed at the show that
Sony was pitching a line of digital
memo recorders that could produce
input directly to DNS.
12:15 - Bill D.
Bob F. , Lernout & Hauspie
has a development relationship with Sony
where we have done extensive work
on speech recognition integration
with their digital audio recorders.
Dragon NaturallySpeaking can
transcribed any high-quality WAV.
file, assuming the user has been
trained for the system.
12:34 - Richard Seltzer
Bob -- yes, the microphone matters
a lot too. You need a good one
(which comes with the software),
and you need to place it right and
consistently (with a headset --
the mouth being a consistent
distance from your mouth). Other
pointers, Bill?
12:35 - Richard Seltzer
Bill -- given the importance of
the microphone and positioning of
the microphone, would it make
sense for an author to record/dictate
onto cassette (virtually anywhere)
and then play the cassette into
a mic/PC running Dragon in order
to get a rough transcript?
12:34 - Hibbspc
My 84 year old mother, now nearly
blind and good typist, but no
longer...is she your market?
12:37 - Richard Seltzer
Bill -- do the blind or people
whose sight is failing use this
product? I suspect it would be
difficult for them, because of the
need to read the screen to check
for errors and correct them. On
the other hand, it would be great
for anyone who has trouble typing
-- either just plain slow or due
to arthritis, etc. I'm thinking of
giving this to my mother (81)
who is having increasing difficulty
dealing with a keyboard.
12:50 - Richard Seltzer
Bill -- What do you see as the
most important/useful directions for
future development (aside from
dealing with multiple voices)?
12:52 - Bill D.
Richard, the biggest research
tasks we have with speech
recognition, is to make it far
more natural. Several things we are
looking at along these lines include:
automatic punctuation,
speaker independence (no training),
and of course multi-voice
conversation as you mentioned.
12:53 - Richard Seltzer
Bill -- I'm really amazed at what
is possible today -- and at an
affordable price. I had thought
that this technology was much
farther from prime time. I had
thought that only applications with
severely limited vocabularies
made sense today. I'm looking forward
to experimenting more with my
version 5.0.
12:56 - Bill D.
Bob, Dragon NaturallySpeaking
will work with virtually any Windows
based application. Any application
that allows for standard text
imput can be speech enabled with
Dragon NaturallySpeaking. We
specifically add commanding control
functions, for limited set of
office productivity applications,
Web tools, and various e-mail
programs.
12:58 - Bob Zwick
Bill D. - that's interesting.
I could be speaking in one audio chat
room and have it transcribed into
another text chat room !
12:58 - Richard Seltzer
Bob Zwick and others -- the command
capabilities of this software
seem to make it natural for embedding
it, combining it with other
Windows apps in creative ways.
I'd love to learn more about what
has already been done along that
line. Anything like that at your
Web site, Bill?
12:59 - Richard Seltzer
Bob Zwick -- I could imagine that
combination of audio and voice
chat being very useful -- even
with PalTalk -- to talk and have
what you say automatically entered
in the text chat window. Would
be great for Global Learn Day
next year so folks without voice
output could still get a pretty
good sense of what's going on.
12:55 - Richard Seltzer
All -- we're just about at the
end of the hour. Please, before
signing off, enter your email
and URL addresses so we can keep in
touch. And please join us again
next Thursday. Bill and all, thanks
very much for joining us today.
12:57 - Bob Zwick
Bob Zwick http://www.cottagemicro.com/coinfo/contact.htm
Voice/Text contact
12:57 - Bill D.
Richard, it has been a pleasure,
thanks so much for inviting me.
This is the first chat session
where a been so actively involved.
It's been fun! My e-mail address
is BDESTEFANIS@LHSL.COM
13:00 - Richard Seltzer
Bill, thanks again. All -- time
to wrap up. Yes, do please enter
your contact info here before
signing off.
13:01 - Bill D.
Richard, thank you, when a transcription
of this conversation is
posted please let me know thanks
again Bill DeStefanis
13:02 - Richard Seltzer
Bill -- Will do. Thanks again.
13:02 - Bob Zwick
Richard - be sure to listen to
my interview on TheReport.Com AM
Radio on Nov. 13 6:30 PM EST
13:03 - Richard Seltzer
Bob Zwick -- Glad to hear that
you hooked up with Bill and Dave.
Yes, I will try to tune in.
13:05 - Bob Zwick
I really like the multiple personalities.
I can ahve one for a
phone bridge, a mic, an audio
chat room and mp3 files !
13:06 - Bob Zwick
Thanks Bill
13:06 - Richard Seltzer
Bob -- Interesting idea. Yes,
that should improve the accuracy of
the transcriptions. You ought
to give it a try.
13:06 - Bob Zwick
bye all
13:06 - Richard Seltzer
Bye.
To connect to the chat room, go to www.samizdat.com/chat-intro.html
The full text of Richard Seltzer's books The Social Web,
Take
Charge of Your Web Site, Shop Online the Lazy Way, and
The
Way of the Web, plus more than a hundred related articles are available
on CD ROM My
Internet: a Personal View of Internet Business Opportunities.
Web
Business Boot Camp: Hands-on Internet lessons for manager, entrepreneurs,
and professionals by Richard Seltzer (Wiley, 2002).
No-nonsense guide targets activities that anyone can perform to achieve
online business
success.
Reviews.
a
library for the price of a book.
This site is Published by B&R Samizdat Express, 33 Gould St., West Roxbury, MA 02132. (617) 469-2269. seltzer@samizdat.com
Return to B&R Samizdat Express
<
| Internet Business Showcase: | ||
|
|
|