BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:STATISTICAL SPEECH SYNTHESIS - Heiga Zen (Toshiba Research Europe 
 Ltd.)
DTSTART:20110111T130000Z
DTEND:20110111T150000Z
UID:TALK28780@talks.cam.ac.uk
CONTACT:Kai Yu
DESCRIPTION:This talk will formulate the speech synthesis problem in a sta
 tistical framework and discuss how it is decomposed into its sub-problems\
 , which include text analysis\, spectral envelope estimation\, acoustic mo
 del training\, speech parameter generation\, and waveform reconstruction. 
  The talk will also describe how these sub-problems are solved in HMM-base
 d speech synthesis.  Some recent trials will also be discussed.
LOCATION: Cambridge University Engineering Department\, Lecture Room 4
END:VEVENT
END:VCALENDAR