Sciweavers

2901 search results - page 309 / 581
» Predicting non-stationary processes
Sort
View
ICASSP
2011
IEEE
14 years 10 months ago
EM-style optimization of hidden conditional random fields for grapheme-to-phoneme conversion
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...
ICASSP
2011
IEEE
14 years 10 months ago
A Kalman-like algorithm with no requirements for noise and initial conditions
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...
Yuriy S. Shmaliy
ICASSP
2011
IEEE
14 years 10 months ago
PAC-Bayesian approach for minimization of phoneme error rate
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...
Joseph Keshet, David A. McAllester, Tamir Hazan
ICASSP
2011
IEEE
14 years 10 months ago
A paired test for recognizer selection with untranscribed data
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...
Bhiksha Raj, Rita Singh, James Baker
ICASSP
2011
IEEE
14 years 10 months ago
Performance optimized predictor blending technique for lossless image coding
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...
Grzegorz Ulacha, Ryszard Stasinski