BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Human-like singing and talking machines: flexible speech synthesis
  in karaoke\, anime\, smart phones\, video games\, digital signage\, TV an
 d radio programs\, etc. - Keiichi Tokuda (Nagoya Institute of Technology /
  Google)
DTSTART:20150206T133000Z
DTEND:20150206T143000Z
UID:TALK56783@talks.cam.ac.uk
CONTACT:Rogier van Dalen
DESCRIPTION:This talk will give an overview of statistical approach to\nfl
 exible speech synthesis.  For constructing human-like talking\nmachines\, 
 speech synthesis systems are required to have an\nability to generate spee
 ch with arbitrary speaker's voice\,\nvarious speaking styles in different 
 languages\, varying emphasis\nand focus\, and/or emotional expressions.  T
 he main advantage of\nthe statistical approach is that such flexibility ca
 n easily be\nrealized using mathematically well-defined algorithms.  In th
 is\ntalk\, the system architecture is outlined and then recent\nresults an
 d demos will be presented.\n\n*Biography*\n\nKeiichi Tokuda is a Professor
  in the Department of Computer Science at Nagoya Institute of Technology a
 nd currently he is visiting Google as sabbatical.  He is also an Honorary 
 Professor at the University of Edinburgh.  He was an Invited Researcher at
  the National Institute of Information and Communications Technology (NICT
 )\, formally known as the ATR Spoken Language Communication Research Labor
 atories\, Kyoto\, Japan from 2000 to 2013\, and was a Visiting Researcher 
 at Carnegie Mellon University from 2001 to 2002.  He has been working on s
 tatistical parametric speech synthesis after he proposed an algorithm for 
 speech parameter generation from HMM in 1995.  He received six paper award
 s and two achievement awards.  He is an IEEE Fellow and an ISCA Fellow.
LOCATION:Department of Engineering - LR6
END:VEVENT
END:VCALENDAR