AES E-Library

L. Álvarez, E. Alexandre, C. Llerena, R. Gil-Pita, and M. Rosa-Zurera, "Combination of Growing and Pruning Algorithms for Multilayer Perceptrons for Speech/Music/Noise Classification in Digital Hearing Aids," Paper 8850, (2013 May.). doi: L. Álvarez, E. Alexandre, C. Llerena, R. Gil-Pita, and M. Rosa-Zurera, "Combination of Growing and Pruning Algorithms for Multilayer Perceptrons for Speech/Music/Noise Classification in Digital Hearing Aids," Paper 8850, (2013 May.). doi:
Abstract: This paper explores the feasibility of combining both growing and pruning algorithms in some way that the global approach results in finding a smaller multilayer perceptron (MLP) in terms of network size, which enhances the speech/music/noise classification performance in digital hearing aids, with the added bonus of demanding a lower number of hidden neurons, and consequently, lower computational cost. With this in mind, the paper will focus on the design of an approach that starts adding neurons to an initial small MLP until the stopping criteria for the growing stage is reached. Then, the MLP size is reduced by successively pruning the least significant hidden neurons while maintaining a continuous decreasing function. The results obtained with the proposed approach will be compared with those obtained when using both growing and pruning algorithms separately.

@article{álvarez2013combination,
author={álvarez, lorena and alexandre, enrique and llerena, cosme and gil-pita, roberto and rosa-zurera, manuel},
journal={journal of the audio engineering society},
title={combination of growing and pruning algorithms for multilayer perceptrons for speech/music/noise classification in digital hearing aids},
year={2013},
volume={},
number={},
pages={},
doi={},
month={may},} @article{álvarez2013combination,
author={álvarez, lorena and alexandre, enrique and llerena, cosme and gil-pita, roberto and rosa-zurera, manuel},
journal={journal of the audio engineering society},
title={combination of growing and pruning algorithms for multilayer perceptrons for speech/music/noise classification in digital hearing aids},
year={2013},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={this paper explores the feasibility of combining both growing and pruning algorithms in some way that the global approach results in finding a smaller multilayer perceptron (mlp) in terms of network size, which enhances the speech/music/noise classification performance in digital hearing aids, with the added bonus of demanding a lower number of hidden neurons, and consequently, lower computational cost. with this in mind, the paper will focus on the design of an approach that starts adding neurons to an initial small mlp until the stopping criteria for the growing stage is reached. then, the mlp size is reduced by successively pruning the least significant hidden neurons while maintaining a continuous decreasing function. the results obtained with the proposed approach will be compared with those obtained when using both growing and pruning algorithms separately.},}

TY - paper
TI - Combination of Growing and Pruning Algorithms for Multilayer Perceptrons for Speech/Music/Noise Classification in Digital Hearing Aids
SP - EP -
AU - Álvarez, Lorena
AU - Alexandre, Enrique
AU - Llerena, Cosme
AU - Gil-Pita, Roberto
AU - Rosa-Zurera, Manuel
PY - 2013
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2013 TY - paper
TI - Combination of Growing and Pruning Algorithms for Multilayer Perceptrons for Speech/Music/Noise Classification in Digital Hearing Aids
SP - EP -
AU - Álvarez, Lorena
AU - Alexandre, Enrique
AU - Llerena, Cosme
AU - Gil-Pita, Roberto
AU - Rosa-Zurera, Manuel
PY - 2013
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2013
AB - This paper explores the feasibility of combining both growing and pruning algorithms in some way that the global approach results in finding a smaller multilayer perceptron (MLP) in terms of network size, which enhances the speech/music/noise classification performance in digital hearing aids, with the added bonus of demanding a lower number of hidden neurons, and consequently, lower computational cost. With this in mind, the paper will focus on the design of an approach that starts adding neurons to an initial small MLP until the stopping criteria for the growing stage is reached. Then, the MLP size is reduced by successively pruning the least significant hidden neurons while maintaining a continuous decreasing function. The results obtained with the proposed approach will be compared with those obtained when using both growing and pruning algorithms separately.