AES E-Library

L. Álvarez, E. Alexandre, and M. Rosa-Zurera, "Pruning Algorithms for Multilayer Perceptrons Tailored for Speech/Non-Speech Classification in Digital Hearing Aids," Paper 7736, (2009 May.). doi: L. Álvarez, E. Alexandre, and M. Rosa-Zurera, "Pruning Algorithms for Multilayer Perceptrons Tailored for Speech/Non-Speech Classification in Digital Hearing Aids," Paper 7736, (2009 May.). doi:
Abstract: This paper explores the feasibility of using different pruning algorithms for multilayer perceptrons (MLPs) applied to the problem of speech/non-speech classification in digital hearing aids. A classifier based on MLPs is considered the best option in spite of its presumably high computational cost. Nevertheless, its implementation has been proven to be feasible: it requires some trade-offs involving a balance between reducing the computational demands (that is, the number of neurons) and the quality perceived by the user. In this respect, this paper will focus on the design of three novel pruning algorithms for MLPs, which attempt to converge to the minimum complexity network (that is, the lowest number of neurons in the hidden layer) without degrading the performance of it. The results obtained with the proposed algorithms will be compared with those obtained when using another pruning algorithm proposed in the literature.

@article{álvarez2009pruning,
author={álvarez, lorena and alexandre, enrique and rosa-zurera, manuel},
journal={journal of the audio engineering society},
title={pruning algorithms for multilayer perceptrons tailored for speech/non-speech classification in digital hearing aids},
year={2009},
volume={},
number={},
pages={},
doi={},
month={may},} @article{álvarez2009pruning,
author={álvarez, lorena and alexandre, enrique and rosa-zurera, manuel},
journal={journal of the audio engineering society},
title={pruning algorithms for multilayer perceptrons tailored for speech/non-speech classification in digital hearing aids},
year={2009},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={this paper explores the feasibility of using different pruning algorithms for multilayer perceptrons (mlps) applied to the problem of speech/non-speech classification in digital hearing aids. a classifier based on mlps is considered the best option in spite of its presumably high computational cost. nevertheless, its implementation has been proven to be feasible: it requires some trade-offs involving a balance between reducing the computational demands (that is, the number of neurons) and the quality perceived by the user. in this respect, this paper will focus on the design of three novel pruning algorithms for mlps, which attempt to converge to the minimum complexity network (that is, the lowest number of neurons in the hidden layer) without degrading the performance of it. the results obtained with the proposed algorithms will be compared with those obtained when using another pruning algorithm proposed in the literature.},}

TY - paper
TI - Pruning Algorithms for Multilayer Perceptrons Tailored for Speech/Non-Speech Classification in Digital Hearing Aids
SP - EP -
AU - Álvarez, Lorena
AU - Alexandre, Enrique
AU - Rosa-Zurera, Manuel
PY - 2009
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2009 TY - paper
TI - Pruning Algorithms for Multilayer Perceptrons Tailored for Speech/Non-Speech Classification in Digital Hearing Aids
SP - EP -
AU - Álvarez, Lorena
AU - Alexandre, Enrique
AU - Rosa-Zurera, Manuel
PY - 2009
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2009
AB - This paper explores the feasibility of using different pruning algorithms for multilayer perceptrons (MLPs) applied to the problem of speech/non-speech classification in digital hearing aids. A classifier based on MLPs is considered the best option in spite of its presumably high computational cost. Nevertheless, its implementation has been proven to be feasible: it requires some trade-offs involving a balance between reducing the computational demands (that is, the number of neurons) and the quality perceived by the user. In this respect, this paper will focus on the design of three novel pruning algorithms for MLPs, which attempt to converge to the minimum complexity network (that is, the lowest number of neurons in the hidden layer) without degrading the performance of it. The results obtained with the proposed algorithms will be compared with those obtained when using another pruning algorithm proposed in the literature.