BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Parametric Speech Synthesis - Heiga Zen (Toshiba)
DTSTART:20090126T130000Z
DTEND:20090126T140000Z
UID:TALK16262@talks.cam.ac.uk
CONTACT:Dr Marcus Tomalin
DESCRIPTION:This seminar gives a general overview of techniques in statist
 ical \nparametric speech synthesis.  One of the instances of these \ntechn
 iques\, called hidden Markov model (HMM)-based speech synthesis\, \nhas re
 cently been demonstrated to be very effective in generating \nacceptable s
 peech synthesis.  This seminar also contrasts these \ntechniques with the 
 more conventional technique of unit-selection \nsynthesis that has dominat
 ed speech synthesis over the last ten years. \n  The advantages and disadv
 antages of statistical parametric synthesis \nare highlighted as well as i
 dentifying where we expect key \ndevelopments to appear in the immediate f
 uture.
LOCATION:LR5\, Engineering Department\, Baker Building
END:VEVENT
END:VCALENDAR