Detecting Communication Errors from visual cues during the system's conversational turnDate:
August 14 2008 Time:
9:00AM to 10:00AM Location:
Sybor Wang, firstname.lastname@example.org
Automatic detection of communication errors in conversational systems typically rely only on acoustic cues; when visual
information has been used to improve error recognition in dialogue systems, it has been limited to observations while the
speaker is communicating vocally. However, perceptual studies have indicated that speakers do exhibit visual communication
error cues passively during the system's conversational turn.
In this thesis, I introduce novel algorithms for face and body gesture recognition and present the first automatic system for
detecting communication errors using facial expressions during the system's turn. This is useful as it detects communication
problems within the same conversation turn. To detect communication problems accurately and efficiently I develop novel
extensions to hidden-state discriminative methods. I will discuss results that show when human subjects become aware that the
conversational system is capable of receiving visual input, they become more communicative visually yet naturally.
See other events that are part of
See other events happening in August 2008