Multilayer perceptron with sparse hidden outputs for phoneme recognition

This paper introduces the sparse multilayer perceptron (SMLP) which learns the transformation from the inputs to the targets as in multilayer perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5336 - 5339
Main Authors Sivaram, G. S. V. S., Hermansky, Hynek
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2011
Subjects
Acoustics
Cost function
Hidden Markov models
machine learning
Multilayer perceptron
Neurons
phoneme recognition
sparse features
Speech
Speech processing
Training
Online AccessGet full text

Cover

More Information
Summary:This paper introduces the sparse multilayer perceptron (SMLP) which learns the transformation from the inputs to the targets as in multilayer perceptron (MLP) while the outputs of one of the internal hidden layers is forced to be sparse. This is achieved by adding a sparse regularization term to the cross-entropy cost and learning the parameters of the network to minimize the joint cost. On the TIMIT phoneme recognition task, the SMLP based system trained using perceptual linear prediction (PLP) features performs better than the conventional MLP based system. Furthermore, their combination yields a phoneme error rate of 21.2%, a relative improvement of 6.2% over the baseline.
ISBN:9781457705380
1457705389
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2011.5947563