BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:New and emerging applications of 'adaptive' speech synthesis' - Ju
 nichi Yamagishi\, Centre for Speech  Technology Research (CSTR) at the Uni
 versity of Edinburgh
DTSTART:20110209T130000Z
DTEND:20110209T150000Z
UID:TALK29709@talks.cam.ac.uk
CONTACT:Kai Yu
DESCRIPTION:Until recently\, text-to-speech was often just an 'optional ex
 tra' which allowed text to be read out loud. But now\, thanks to HMM and s
 peaker adaptation technologies\, which were originally developed for  ASR\
 , speech synthesis can mean more than just the reading out of text in a pr
 edefined voice. New research areas and more interesting applications are e
 merging. In this talk\, after a quick overview of the basic approaches to 
 statistical speech synthesis including speaker adaptation\, we consider so
 me of these new applications of speech synthesis. We look behind each appl
 ication at the underlying theoretical techniques used and describe the sci
 entific advances that have made them possible. The applications we will ex
 amine include personalised speech-to-speech translation\, clinical applica
 tions such as voice reconstruction for patients who have disordered speech
 \, and noise-adaptive speech synthesis. The techniques we will examine inc
 lude structural adaptation approaches\, unsupervised adaptation\, multi-pa
 ss architecture\, and cross-lingual adaptation for speech synthesis.
LOCATION:Cambridge University Engineering Department\, Lecture Room 4
END:VEVENT
END:VCALENDAR