BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling trajectories in statistical speech synthesis - Matt Shan
 non (Cambridge) and Heiga Zen (Toshiba Research Europe Ltd.)
DTSTART:20110126T130000Z
DTEND:20110126T150000Z
UID:TALK29337@talks.cam.ac.uk
CONTACT:Kai Yu
DESCRIPTION:In statistical speech synthesis we build a probabilistic model
  of (processed) speech given (processed) text. The processed speech is in 
 the form of a sequence of acoustic feature vectors\, and the sequence over
  time of each component of this feature vector forms a trajectory. In this
  talk we'll discuss how to model these trajectories.\n\nWe will first revi
 ew a few ways in which the standard HMM synthesis model is unsatisfactory.
  In particular the standard model is unnormalized\, and we'll discuss the 
 practical impact of this lack of normalization. We'll then look at normali
 zed approaches\, including the trajectory HMM (a globally normalized model
 ) and the autoregressive HMM (a locally normalized model). Finally we'll d
 iscuss some other possible enhancements including minimum generation error
  (MGE) training.
LOCATION: Cambridge University Engineering Department\, Lecture Room 2
END:VEVENT
END:VCALENDAR