----- Original Message -----
From: alewins <[log in to unmask]>
To: <[log in to unmask]>
Sent: Thursday, July 27, 2000 9:46 PM
Subject: Re: Voice recognition software
> > I am interested in whether anyone who is on the list has used voice
> > recognition software to transcribe interviews for qualitative data
> analysis.
> > I understand from someone who uses the software that some of the
software
> > can be "trained" to listen to multiple voices, and some only recognizes
> one
> > user's voice. Does anyone know any more information about this? Are
you
> > aware of softare that can recognize multiple voices?
> >
> > Any information would be appreciated!
> >
> > Beth Sperber Richie, Ph.D.
> > (301) 523-8882
>
> Beth - I hope someone gets back to you with more positive information, but
> for now
> I append various sites below referring to VR software- frankly not sure
> whether they will lead you to a discovery of 'multiple voice' recognition
> software.
> The virtue of speech recognition software of course is that it might save
> transcription. You could consider instead relying on the access to the
> entire video or audio file on your computer and the limited transcription
of
> important parts of it - or summaries, and the linking of those summaries
or
> commentaries, to the relevant part of the audio (always of course in
context
> with the whole)
> ....a budget software has just been launched, CTANKS, developed by Alan
> Cartwright ( I have no personal experience of working with it yet) which:-
> Plays and allows transcription of audio and video files (in house
> transcription s/w) - Allows ' hyper links' to be built in transcription
to
> points in the originating multi media files (or other files) - (therefore
> possible reduction in need to transcribe whole file - or to enable replay
of
> important situation)
> - Note taking features - Assign codes to transcribed text segments -
Text
> retrieval by codes - Searching facilities
>
> its web site is www.code-a-text.co.uk
>
> The fact thats its at a very budget price means that it might be worth
> taking a gamble ... however always of course, check system specifications
on
> all multi media software. Ensure your computer has the space for it, the
> right peripherals ...and sufficient RAM. But as with most software
> developers of qualitative software, Alan Cartright will give you lots of
> support.
> Other softwares which also provide the possibility of working
> with/analysing/integrating multi media data
> ATLAS.ti www.atlasti.de (direct integration and coding of
> audio/video files)
> QSR NVivo www.qsr.com.au (coding of the text -maybe a summary?- at
> which there is a link to any multimedia file )
>
> Also browse old messages re VR on the list at
> http://www.mailbase.ac.uk/lists/qual-software/archive.html
>
> Below: a list of Voice Recognition or VR resource sites - youmight find
> onward links from here which give you more info.
>
> http://www.infoworld.com/cgi-bin/displayTC.pl?/reviews/970901conspeech.htm
> review on ViaVoice and Dragon Naturally speaking
>
> http://www.zdnet.co.uk/pcmag/flooks/1998/05/viavoice_gold.html
> IBM Viavoice site
> http://www.research.microsoft.com/srg/srproject.asp
> Microsoft 'whisper' speech recognition development
>
> http://hawaii.psychology.msstate.edu/Speech.html
> Automatic speech recognition lab>
>
>
> OK - good luck and let us know if you do find the multiple voice software!
> Ann Lewins
> CAQDAS Networking project
>
I also would be very interested. I have used IBM Viavoice and Dragon
Naturally Speaking, and prefer Viavoice. Dragon still doesn't work
effectively as the speed I speak, and Viavoice required less editing.
However, I still think that I can type just as fast after I take the editing
inot account.
I like the 7 pound/hour girls someone mentioned the other day - send them,
to Australia when you are finished :-))
Peter French
Melbourne, Australia
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|