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: seeking auto transcribing for a small meeting From:"Edgar D' Souza" <edgar -dot- b -dot- dsouza -at- gmail -dot- com> To:"Lisa Priester" <lpriester -at- castandcrew -dot- com> Date:Sat, 4 Aug 2007 10:07:50 +0530
Lisa:
As you say, most of the current crop of voice-recog software need to
be trained to a particular individual. If your SMEs are reluctant to
write or type, I don't even think it possible they'll agree to go
through an enrolment process with your voice-recog tool :-) since not
only is it time-consuming, it also induces a mild feeling of... um..
embarrassment? :)
As John says, trying to voice-recog SME mumbles could be a really
painful process! And once you have text in a doc, /then/ you need to
pound that keyboard, re-shaping it into good text. :-/
Suggestion:
If you can get a DVR that simply records, at good quality, everything
that is said at a meeting (including where you raise your hand when
someone mumbles, and re-state it clearly for the recorder) then
possibly you could use your copy of Dragon or ViaV on your computer to
re-dictate the content you want in the document. Your headphones are
playing back from your DVR, which you pause every few sentences,
re-compose the facts in your head, and dictate a much better version
of what was said into your microphone, which feeds the voice-recog
software. Since you're digesting the raw info and re-wording it
/before/ dictating to ViaV/Dragon, you have less
re-shaping/wordsmithing to do; since you've trained your voice-recog
s/w to your voice and diction, you ought to get 90+% accuracy on the
recognition. So your transcription phase will take a bit longer than
the original meetings, but it's more feasible, IMHO, than trying to
auto-transcribe, at pretty low accuracy, the meandering mumblings of
SMEs.
HTH,
Ed.
On 8/3/07, Lisa Priester <lpriester -at- castandcrew -dot- com> wrote:
> So I've been asked to find out whether anyone knows of some digital recorder
> and transcription software that would work in a small meeting setting, in
> which I and a manager would interview the SME to capture the needed info. I
> know of software such as DragonNaturallySpeaking and ViaVoice, but those
> seemed to be design for use by one person with a headset plugged into
> his/her desktop.
>
> Is anyone familiar with a setup that would allow two or three people to be
> recorded and their words automatically transcribed?
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Create HTML or Microsoft Word content and convert to Help file formats or
printed documentation. Features include support for Windows Vista & 2007
Microsoft Office, team authoring, plus more. http://www.DocToHelp.com/TechwrlList
True single source, conditional content, PDF export, modular help.
Help & Manual is the most powerful authoring tool for technical
documentation. Boost your productivity! http://www.helpandmanual.com
---
You are currently subscribed to TECHWR-L as archive -at- web -dot- techwr-l -dot- com -dot-
