> Date: Mon, 13 Oct 1997 13:56:53 GMT
> To: [log in to unmask]
> From: [log in to unmask] (A.Simpson)
> Subject: Speech recognition software
> Reply-to: [log in to unmask]
> Does anyone know if any of this is robust enough to convert taped speech to
> text - i.e. taped lectures?
If I remember rightly, somebody at Edinburgh University was working
in tandem with the local Computing Services to use a high spec
PC & Kurzweil Voice with a DAT recording of the lecture. They
had written some special software to accentuate pauses in to those
large for use with Kurzweil. This was around the beginning of the
year and was at a Talking Technologies seminar in South London (a
college if I recall).
As Phil Satchell mentioned, they had one or two 'guinea pig'
lecturers who had very well trained voice profiles. I can't remember
the individuals name, but perhaps someone else may be able to?
Regards
Matthew Dodd
CELT - Technical
---------------------------------------------------
Matthew Dodd, Technician
Centre for Enabling & Learning Technologies
University of Southampton New College, Southampton, Hants
Mobile: 0468 903930 Tel: 01703 330100
Email : [log in to unmask]
[log in to unmask]
WWW: http://www.celt.lsu.soton.ac.uk/
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
