Humanist Discussion Group, Vol. 14, No. 595.
Centre for Computing in the Humanities, King's College London
<http://www.princeton.edu/~mccarty/humanist/>
<http://www.kcl.ac.uk/humanities/cch/humanist/>
Date: Mon, 15 Jan 2001 06:58:08 +0000
From: lachance@chass.utoronto.ca (Francois Lachance)
Subject: Re: 14.0588 teleprompto
Willard,
It may well be that the old errors of transcription (sound to script)
and errors of prononciation (script to sound) offer some multimedia
ground for research in artificial intelligence. Consider that machines
could subvocalize a verbal string in order to catch errors not usually
caught by now currently standard spell-checkers. One of my favourites
crossed my screen recently on a snowy winter day when a colleague no
doubt dreaming of a spring thaw sent out a messge beginning with "May
apologies". It foolws that voic recognition software may be improved by
being coupled with grammar & spell checkers. Perhaps the folks involved
in natural language processing might venture a comment or comet. ***>
--
Francois Lachance, Scholar-at-large
http://www.chass.utoronto.ca/~lachance
Member of the Evelyn Letters Project
http://www.chass.utoronto.ca/~dchamber/evelyn/evtoc.htm
This archive was generated by hypermail 2b30 : 01/15/01 EST