TechWhirl (TECHWR-L) is a resource for technical writing and technical communications professionals of all experience levels and in all industries to share their experiences and acquire information.
For two decades, technical communicators have turned to TechWhirl to ask and answer questions about the always-changing world of technical communications, such as tools, skills, career paths, methodologies, and emerging industries. The TechWhirl Archives and magazine, created for, by and about technical writers, offer a wealth of knowledge to everyone with an interest in any aspect of technical communications.
Subject:Re: Using voice/speech-recognition software From:Gerry Gaffney <Gerry -at- INFODESIGN -dot- COM -dot- AU> Date:Thu, 5 Aug 1999 20:47:03 +1000
I used IBM's Via Voice on an Pentium 150 about a year ago.
The machine was underpowered for the task, so recognition was quite slow.
I found the performance pretty good, but didn't do any measures of
percentage of mistaken words or the like, largely because I expected the
software to get better once I had 'trained' it as recommended in the
documentation.
To my surprise the recognition level got worse after training, so I ended up
un-installing the software.
Other people have told me they got excellent results with Via Voice, so I've
tended to put it down to running under-powered hardware.
Incidentally, Ben Schneidermann asks his audiences how many people have used
voice recognition software, and how many people currently use it. At the
session I attended in Melbourne, about half the audience had used it; none
were current users. Schneidermann says he's found the same results even in
the most technologically sophisticated audiences.
- Gerry
_____________________
Gerry Gaffney
Information & Design
PO Box 1255
Windsor VIC 3181
Australia
_____________________
----- Original Message -----
From: Lori Kipnes-Bailen <lkbailen -at- BOSCOM -dot- COM>
To: <TECHWR-L -at- LISTSERV -dot- OKSTATE -dot- EDU>
Sent: Thursday, 5 August 1999 6:36
Subject: Using voice/speech-recognition software
> Hi,
>
> I did a search of the archives on voice/speech
> recognition software, but I need some more information
> from those of you who are actually using it.
>
> 1. What kind of work are you doing with it (e.g.,
> primarily translation, manual composition,
> white papers)?
>
> 2. How long is the startup?
>
> 3. How accurate is it? Of 100 words, how many
> do you have to correct? What about punctuation?
>
> 4. Does environmental noise affect the software? We
> are in an open cubicle environment (and I keep having
> nightmares about that Dilbert cartoon where someone
> looks over Dilbert's shoulder and yells, "Close!").
>
> 5. What are the optimal system requirements?
>
> Our general manager is really "into" this. I have to decide
> if it is worth it for us. Since I have an RSI tendency in
> my right wrist, I suppose I should just go for it while he's
> offering, but I want to make a more educated decision.
> Plus, I would like some comparison information about
> different products and that sort of "had-I-only-known-when-
> I-started" information that the seller doesn't give you.
>
> If you have experience with this, please share it. I am
> on digest, so I'd appreciate a copy sent to me.
>
> Thanks,
> Lori
>
>
> ----------
> Lori Kipnes-Bailen
> Technical Communicator
>
> Better On-line Solutions, Ltd.
> Teradyon Industrial Park
> Misgav, 20179 Israel
> Tel. +972-4-990-7582
> Fax +972-4-999-0334
> lkbailen -at- boscom -dot- com
>
>
From ??? -at- ??? Sun Jan 00 00:00:00 0000=
>
>
>
>
