BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Speech Dasher: Fast Writing using Speech and Gaze - Keith Vertanen
 \, University of Cambridge
DTSTART:20100329T100000Z
DTEND:20100329T102000Z
UID:TALK23464@talks.cam.ac.uk
CONTACT:Keith Vertanen
DESCRIPTION:Speech Dasher allows writing using a combination of speech and
  a zooming interface. Users first speak what they want to write and then t
 hey navigate through the space of recognition hypotheses to correct any er
 rors. Speech Dasher’s model combines information from a speech recognize
 r\, from the user\, and from a letter-based language model. This allows fa
 st writing of anything predicted by the recognizer while also providing se
 amless fallback to letter-by-letter spelling for words not in the recogniz
 er’s predictions. In a formative user study\, expert users wrote at 40 (
 corrected) words per minute. They did this despite a recognition word erro
 r rate of 22%. Furthermore\, they did this using only speech and the direc
 tion of their gaze (obtained via an eye tracker).\n\nFor more information\
 , see the "4-page CHI note":http://www.keithv.com/pub/sd or chapter 4 of m
 y "thesis":http://www.keithv.com/pub/phd\n\nThis will be a short talk.\n\n
 \n
LOCATION:TCM Seminar Room\, Cavendish Laboratory\, Department of Physics
END:VEVENT
END:VCALENDAR