BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Can we hear people think\, can we discern genuine laughter … and
  can a computer do it better? - Tal Sobol-Shikler (Computer Laboratory\, U
 niversity of Cambridge)
DTSTART:20061207T141500Z
DTEND:20061207T150000Z
UID:TALK5985@talks.cam.ac.uk
CONTACT:Daniel Bernhardt
DESCRIPTION:In this talk I will present an automatic inference system of e
 xpressions of emotions and mental states from non-verbal speech which outp
 erforms human accuracy. The inference is based on a new set of vocal featu
 res including music derived features that have not been used before in thi
 s context. I will describe how an arbitrary set of expressions can be used
  to automatically map a set of several hundred lexical definitions of ment
 al states using the inference machine\, and find the vocal correlates of a
  lexically oriented topology of mental states. I will also show how findin
 gs from one language (English) can be used to automatically infer expressi
 ons in another language (Hebrew)\, demonstrating expressions in human-comp
 uter interaction (HCI) which involves decision-making\, the complex behavi
 our of expressions in time\, and the verification through multi-modal and 
 context analysis.
LOCATION:Rainbow Room\, Computer Laboratory
END:VEVENT
END:VCALENDAR