This work addresses the problem of document image analysis, and more particularly the topic of document structure recognition in old, damaged and handwritten document. The goal of...
Being able to recognize people from their voice is a natural ability that we take for granted. Recent advances have shown significant improvement in automatic speaker recognition ...
We are investigating computational models for humancomputer interaction based on a uniform, declarative, knowledge representation. We describe a new implementation of our work cal...
In this paper, a novel method for speaker adaptation using bilinear model is proposed. Bilinear model can express both characteristics of speakers (style) and phonemes across spea...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...