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...
The paper presents a virtual reality modeling system based on interactive web technologies. The system’s goal is to provide a user-friendly virtual environment for the developme...
We propose a shape population metric that reflects the interdependencies between points observed in a set of examples. It provides a notion of topology for shape and appearance m...
We address the problem of keyword spotting in continuous speech streams when training and testing conditions can be different. We propose a keyword spotting algorithm based on spa...
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...