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...
We propose an unbounded-depth, hierarchical, Bayesian nonparametric model for discrete sequence data. This model can be estimated from a single training sequence, yet shares stati...
We consider Gaussian multiresolution (MR) models in which coarser, hidden variables serve to capture statistical dependencies among the finest scale variables. Tree-structured MR ...
Myung Jin Choi, Venkat Chandrasekaran, Alan S. Wil...
Shannon's Noisy-Channel model, which describes how a corrupted message might be reconstructed, has been the corner stone for much work in statistical language and speech proc...
A cost-sensitive extension of boosting, denoted as asymmetric boosting, is presented. Unlike previous proposals, the new algorithm is derived from sound decision-theoretic princip...