BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Use of Deep Learning in Spoken Dialogue Systems - Steve Young 
 (University of Cambridge)
DTSTART:20171121T133000Z
DTEND:20171121T143000Z
UID:TALK95656@talks.cam.ac.uk
CONTACT:Guy Edward Toh Emerson
DESCRIPTION:Spoken dialogue systems (SDS) provide the core enabling techno
 logy for building intelligent personal assistants.  The function of an SDS
  is to understand each user input\, decode the users intention or goal and
  then respond accordingly.   Whereas historically much of this functionali
 ty has been provided by hand-crafted rule systems\, modern systems increas
 ingly rely on statistical models and machine learning.   This talk will re
 view the structure and components of a modern SDS and their implementation
  using deep neural networks.   The provision of adequate quantities of ann
 otated training data is a major limitation on progress and the talk will c
 onclude by discussing ways in which this bottleneck might be eliminated.
LOCATION:Cripps Court\, Magdalene College
END:VEVENT
END:VCALENDAR