Sciweavers

54 search results - page 5 / 11
» Neural Network Recognition of Spelling Errors
Sort
View
ICASSP
2009
IEEE
13 years 11 months ago
Neural network based language models for highly inflective languages
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture impo...
Tomas Mikolov, Jirí Kopecký, Lukas B...
ANNPR
2008
Springer
13 years 9 months ago
Supervised Incremental Learning with the Fuzzy ARTMAP Neural Network
Abstract. Automatic pattern classifiers that allow for on-line incremental learning can adapt internal class models efficiently in response to new information without retraining fr...
Jean-François Connolly, Eric Granger, Rober...
TSMC
2002
119views more  TSMC 2002»
13 years 7 months ago
A cloning approach to classifier training
The Al-Alaoui algorithm is a weighted mean-square error (MSE) approach to pattern recognition. It employs cloning of the erroneously classified samples to increase the population o...
M. A. Al-Alaoui, R. Mouci, M. M. Mansour, Rony Fer...
ICASSP
2009
IEEE
13 years 5 months ago
Phonological features in discriminative classification of dysarthric speech
In an attempt to overcome problems associated with articulatory limitations and generative models, this work considers the use of phonological features in discriminative models fo...
Frank Rudzicz
INTERSPEECH
2010
13 years 2 months ago
On speaker adaptive training of artificial neural networks
In the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The us...
Jan Trmal, Jan Zelinka, Ludek Müller