Sciweavers

7 search results - page 2 / 2
» Sparse modeling of neural network posterior probabilities fo...
Sort
View
EMNLP
2010
13 years 2 months ago
Training Continuous Space Language Models: Some Practical Issues
Using multi-layer neural networks to estimate the probabilities of word sequences is a promising research area in statistical language modeling, with applications in speech recogn...
Hai Son Le, Alexandre Allauzen, Guillaume Wisniews...
NIPS
1998
13 years 6 months ago
Controlling the Complexity of HMM Systems by Regularization
This paper introduces a method for regularization of HMM systems that avoids parameter overfitting caused by insufficient training data. Regularization is done by augmenting the E...
Christoph Neukirchen, Gerhard Rigoll