We investigate a recently proposed Bayesian adaptation method for building style-adapted maximum entropy language models for speech recognition, given a large corpus of written la...
We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implemenf the idea. The learned model abstracts away ...
In Handwritten Character Recognition, the rejection of extraneous patterns, like image noise, strokes or corrections, can improve significantly the practical usefulness of a syste...
Javier Cano, Joaquim Arlandis, Juan Carlos P&eacut...
Abstract. In this work we present two algorithms of irregular scatter/gather operations based on the binomial tree and Tr¨aff algorithms. We use the prediction provided by hetero...
Kiril Dichev, Vladimir Rychkov, Alexey L. Lastovet...
We report results on the performance of the combination of soft keyboards and marking menus. A model of expert user performance indicated an 11 - 37% (depending on the keyboard la...