BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Context modelling in HMM based speech synthesis - Kai Yu (Cambridg
 e University)
DTSTART:20110316T123000Z
DTEND:20110316T140000Z
UID:TALK30252@talks.cam.ac.uk
CONTACT:Kai Yu
DESCRIPTION:The use of rich contexts is one of the main differences of HMM
  based speech synthesis compared to speech recognition. The most widely us
 ed modelling approach is context-dependent HMM with parameter sharing. Thi
 s talk will discuss the nature of contexts and several structured approach
 es for modelling rich contexts. \n
LOCATION:Cambridge University Engineering Department\, Lecture Room 4
END:VEVENT
END:VCALENDAR