The MILAN project, a joint effort involving Arizona State University and New York University, has produced and validated fundamental techniques for the realization of efficient, r...
Spoken dialogue systemperformance canvary widely fordifferentusers, aswell for the same userduring different dialogues.This paper presents the design and evaluation ofan adaptive v...
We introduce a modified Kalman filter that performs robust, real-time outlier detection, without the need for manual parameter tuning by the user. Systems that rely on high quali...
This paper investigates the automatic analysis and segmentation of meetings. A meeting is analysed in terms of individual behaviours and group interactions, in order to decompose e...
We describe a system for automatically extracting dynamics of tongue gestures from ultrasound images of the tongue using translational deep belief networks (tDBNs). In tDBNs, a jo...