We have recently proposed an EM-style algorithm to optimize log-linear models with hidden variables. In this paper, we use this algorithm to optimize a hidden conditional random ...
Georg Heigold, Stefan Hahn, Patrick Lehnen, Herman...
We address a Kalman-like estimator for solving universally the problems of filtering (p = 0), prediction (p > 0), and smoothing (p < 0) of discrete time-varying state-space...
We describe a new approach for phoneme recognition which aims at minimizing the phoneme error rate. Building on structured prediction techniques, we formulate the phoneme recogniz...
Traditionally, the use of untranscribed speech has been restricted to unsupervised or semi-supervised training of acoustic models. Comparison of recognizers has required labeled d...
The paper presents a lossless coding method based on predictor blending approach that codes nine widely used benchmark images with the lowest average bitrate ever published. At th...