Hi John,

Sorry to get back with you so late, this last week has been very busy.

John wrote from an earlier post:
€œDragon Naturally Speaking now produces real-time transcripts for many large
court cases, running on a laptop!€�

John wrote:
€œYou have now. The majority of Court transcripts in Australia for major
cases are handled with voice-recognition. The court reporter listens to the
case on headphones and repeats what was said into their headset. They use
Dragon Naturally Speaking to type up the transcript, in close-to-real-time.€�


This is really a poor demonstration, the way it was originally posted, it
implied that a microphone was set up in the court room and magically the
court records would be transcribed. That is reason why I brought up the
questions. €œIn regarding accuracy, problems, how much human intervention,
etc. with this program.€�


John wrote:
€œThat example does not prove your case :-) You are quite correct: it's an
intense technical challenge, but the Chinese Whispers experiment is about
memory. The challenge in speech-to-text is that humans are appalling
speakers :-)€�


If I take two groups; one a multicultural group of English speaking
strangers vs. a group of English speaking group of long time friends, Im
sure that the group of English speaking group of long time friends would do
much better then the multicultural group. Therefore, to say that the Chinese
Whispers experiment is about memory is not correct. However, it consists of
both memory and our ability to understand what is being said. People are like
the Dragon Naturally Speaking program in the sense that if we are around a
foreign born speaker who we dont understand very well for a long enough
time, our ability to understand them improves.


John wrote:
€œThis is "particular speaker" transcription. Each court reporter spends a
long time training the software. They have been selected for their ability
to speak clearly, and trained to dictate. Their accuracy is in the order of
one character error per legal page. But they do it all day for a living!€�

John wrote:
€œThe challenge in speech-to-text is that humans are appalling
speakers :-)€�


Better to be said that Speech Recognition is not ready for prime time,
except for certain cases. For computers were made for man rather then man
made for computers. Ever since computers have been created they have been
adapted for humans, one of the biggest challenges has been how to make
computers even more friendly and intuitive because people tend to be very
impatient with computers. A couple of the limiting factors on technology are
peoples willingness to try new technology and his willingness to learn.


John wrote:
You don't send that many TXT messages, right?? :-) If you did, you would be
now be reading to kill auto suggestion :-) Seriously: handwriting
recognition has a big future, as does auto suggestion. However, those of us
who have learned to type find that typing is faster than either speaking,
handwriting, or autosuggestion.


I have sent a few TXT messages, I do not think that its auto suggestion is
the problem but Fat Fingers and lousy interface has been the biggest problem.
In addition, comparing cell phone with that of a personal computer is like
comparing apples to oranges. The Pocket PC interface and the 20 year old DOS
program Mindreader is a much closer example. Another point auto suggestion
is not trying to replace typing or discourage typing but to enhance typing.



Mark wrote:
Last point, many people today are making their decision whether or not they
are buying a piece of software based upon the return on their investment. If
it is not significant, they will be just as happy using their old piece of
software. My hope is that this idea and others may be something that will cause people to upgrade.

John wrote:
Put your money into "collaboration" and "decision support". Most of the
information we want has already been typed: it's sharing it around that's
today's problem :-)

This is probably true for companies larger then 25 employees and for global
and national companies. However, for local companies of less then 25
employees and individuals, collaboration and decision support has much less
significance. Also companies larger then 25 employees and esp. global and
national companies are the type who would most likely to have a licensing
agreement with Microsoft.


John wrote:
Yeah: I'm not quite at the 60 mark myself, I don't think :-) However, I
challenge you to be quicker at typing AND correcting AND formatting with
autosuggestion. That's my point :-)

I am not arguing that with auto suggestion that typing AND correcting AND
formatting will be eliminated but reduced. The challenge will only be proven
when someone creates a modern version of Auto Suggestion on the PC. Then I
will be able to post €œI Told You So!!!€� :-)

Thanks,

Mark Stapel