BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient computer interfaces using continuous gestures\, language
  models\, and speech - Keith Vertanen\, Inference Group
DTSTART:20050621T153000Z
DTEND:20050621T160000Z
UID:TALK4372@talks.cam.ac.uk
CONTACT:Phil Cowans
DESCRIPTION:Despite advances in speech recognition technology\, users of d
 ictation systems still face a significant amount of work to correct errors
  made by the recognizer.  The goal of this work is to investigate the use 
 of a continuous gesture-based data entry interface to provide an efficient
  and fun way for users to correct recognition errors.  Towards this goal\,
  techniques are investigated which expand a recognizer's results to help c
 over recognition errors.  Additionally\, models are developed which utiliz
 e a speech recognizer's n-best list to build letter-based language models.
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR