Sciweavers

111 search results - page 1 / 23
» Discriminative training methods for language models using co...
Sort
View
ICASSP
2010
IEEE
13 years 4 months ago
Discriminative training methods for language models using conditional entropy criteria
This paper addresses the problem of discriminative training of language models that does not require any transcribed acoustic data. We propose to minimize the conditional entropy ...
Jui-Ting Huang, Xiao Li, Alex Acero
INTERSPEECH
2010
12 years 11 months ago
Semi-supervised training of Gaussian mixture models by conditional entropy minimization
In this paper, we propose a new semi-supervised training method for Gaussian Mixture Models. We add a conditional entropy minimizer to the maximum mutual information criteria, whi...
Jui-Ting Huang, Mark Hasegawa-Johnson
ICASSP
2008
IEEE
13 years 11 months ago
A GIS-like training algorithm for log-linear models with hidden variables
Conditional Random Fields (CRFs) are often estimated using an entropy based criterion in combination with Generalized Iterative Scaling (GIS). GIS offers, upon others, the immedi...
Georg Heigold, Thomas Deselaers, Ralf Schlüte...
ACL
2004
13 years 6 months ago
Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
Brian Roark, Murat Saraclar, Michael Collins, Mark...
ACL
2008
13 years 6 months ago
Language Dynamics and Capitalization using Maximum Entropy
This paper studies the impact of written language variations and the way it affects the capitalization task over time. A discriminative approach, based on maximum entropy models, ...
Fernando Batista, Nuno J. Mamede, Isabel Trancoso