The World Wide Web currently has a huge amount of data, with practically no classification information, and this makes it extremely difficult to handle effectively. It has been re...
This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-ofvocabulary words and as a method for lexicon compressi...
Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is...
We propose an efficient system for realistic speech animation. The system supports all steps of the animation pipeline, from the capture or design of 3D head models up to the synth...
We propose a method for choosing the number of colors or true gray levels in an image; this allows fully automatic segmentation of images. Our underlying probability model is a hid...