BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Belief Networks for Phone Recongition - Rory Waite  and Matt 
 Seigel (University of Cambridge)
DTSTART:20110310T143000Z
DTEND:20110310T160000Z
UID:TALK29125@talks.cam.ac.uk
CONTACT:Shakir Mohamed
DESCRIPTION:The current state-of-the-art for acoustic models are Discrimin
 atively trained Hidden Markov Models. There are proposals to use different
  types of model to improve upon the current state-of-the-art. One model is
  the\nDeep Belief Network that can produce a rich distributed representati
 on of speech data. We describe Restricted Boltzmann Machines\, how they ar
 e composed into a Deep Belief Network\, and the application of a Deep Beli
 ef Network to phone recognition. If we have time we will touch on another 
 deep structured acoustic model\, the deep hidden conditional random field.
 \n\nThis is outlined in the paper\nhttp://www.cs.toronto.edu/~gdahl/papers
 /dbnPhoneRec.pdf
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR