BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Nonparametric Bayesian Word Discovery by Robots: Introduction to S
 ymbol Emergence in Robotics -  Dr. Tadahiro Taniguchi\, College of Informa
 tion Science and Engineering\, Ritsumeikan University. 
DTSTART:20160909T143000Z
DTEND:20160909T150000Z
UID:TALK67394@talks.cam.ac.uk
CONTACT:Josie Hughes
DESCRIPTION:Word discovery from speech signals is a crucial task for a hum
 an infant to learn a language.  Differently from conventional approach tow
 ards automatic speech recognition\, infants cannot use labeled data\, i.e.
 \, transcribed text. They have to discover words from speech signals and l
 earn meanings of the words in an unsupervised manner. We have been develop
 ing machine learning methods that enable a robot to learn words automatica
 lly.  In this talk\, I am introducing two unsupervised machine learning me
 thods.\nOne is for simultaneous learning of lexicons and object categories
  using multimodal latent Dirichlet allocation (MLDA) and nested Pitman-Yor
  language model (NPYLM).  The other is nonparametric Bayesian double artic
 ulation analyser (NPB-DAA) for learning phonemes and words directly from s
 peech signals using hierarchical Dirichlet process hidden language model (
 HDP-HLM). The both methods are based on Bayesian nonparametrics. I am also
  introducing our research field called symbol emergence in robotics.
LOCATION:CUED\, LR5
END:VEVENT
END:VCALENDAR