In this paper, we investigate a simple, mistakedriven learning algorithm for discriminative training of continuous density hidden Markov models (CD-HMMs). Most CD-HMMs for automat...
Paper plays a crucial role in many developing world information practices. However, paper-based records are inefficient, error-prone and difficult to aggregate. Therefore we need ...
This paper presents a study of finger-based text entry for mobile devices with touchscreens. Many devices are now coming to market that have no physical keyboards (the Apple iPhon...
Poor literacy remains a decisive barrier to the economic empowerment of many people in the developing world. Of particular importance is literacy in a widely spoken "world la...
Matthew Kam, Divya Ramachandran, Varun Devanathan,...
We present the Motion Presence application, an augmented phone book style application that allows close friends and family to view each other's current motion status ("m...