AES E-Library

L. Álvarez, C. Llerena, E. Alexandre, R. Gil-Pita, and M. Rosa-Zurera, "Selection of Approximated Activation Functions in Neural Network-Based Sound Classifiers for Digital Hearing Aids," Paper 8453, (2011 May.). doi: L. Álvarez, C. Llerena, E. Alexandre, R. Gil-Pita, and M. Rosa-Zurera, "Selection of Approximated Activation Functions in Neural Network-Based Sound Classifiers for Digital Hearing Aids," Paper 8453, (2011 May.). doi:
Abstract: The feasible implementation of signal processing techniques on hearing aids is constrained to the limited number of instructions per second to implement the algorithms on the digital signal processor the hearing aid is based on. This adversely limits the design of a neural network-based classifier embedded in the hearing aid. Aiming at helping the processor achieve accurate enough results, and in the effort of reducing the number of instructions per second, this paper focuses on exploring the most adequate approximations for the activation function. The experimental work proves that the approximated neural network-based classifier achieves the same efficiency as that reached by exact networks (without these approximations), but, this is the crucial point, with the added advantage of extremely reducing the computational cost on digital signal processor.

@article{álvarez2011selection,
author={álvarez, lorena and llerena, cosme and alexandre, enrique and gil-pita, roberto and rosa-zurera, manuel},
journal={journal of the audio engineering society},
title={selection of approximated activation functions in neural network-based sound classifiers for digital hearing aids},
year={2011},
volume={},
number={},
pages={},
doi={},
month={may},} @article{álvarez2011selection,
author={álvarez, lorena and llerena, cosme and alexandre, enrique and gil-pita, roberto and rosa-zurera, manuel},
journal={journal of the audio engineering society},
title={selection of approximated activation functions in neural network-based sound classifiers for digital hearing aids},
year={2011},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={the feasible implementation of signal processing techniques on hearing aids is constrained to the limited number of instructions per second to implement the algorithms on the digital signal processor the hearing aid is based on. this adversely limits the design of a neural network-based classifier embedded in the hearing aid. aiming at helping the processor achieve accurate enough results, and in the effort of reducing the number of instructions per second, this paper focuses on exploring the most adequate approximations for the activation function. the experimental work proves that the approximated neural network-based classifier achieves the same efficiency as that reached by exact networks (without these approximations), but, this is the crucial point, with the added advantage of extremely reducing the computational cost on digital signal processor.},}

TY - paper
TI - Selection of Approximated Activation Functions in Neural Network-Based Sound Classifiers for Digital Hearing Aids
SP - EP -
AU - Álvarez, Lorena
AU - Llerena, Cosme
AU - Alexandre, Enrique
AU - Gil-Pita, Roberto
AU - Rosa-Zurera, Manuel
PY - 2011
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2011 TY - paper
TI - Selection of Approximated Activation Functions in Neural Network-Based Sound Classifiers for Digital Hearing Aids
SP - EP -
AU - Álvarez, Lorena
AU - Llerena, Cosme
AU - Alexandre, Enrique
AU - Gil-Pita, Roberto
AU - Rosa-Zurera, Manuel
PY - 2011
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2011
AB - The feasible implementation of signal processing techniques on hearing aids is constrained to the limited number of instructions per second to implement the algorithms on the digital signal processor the hearing aid is based on. This adversely limits the design of a neural network-based classifier embedded in the hearing aid. Aiming at helping the processor achieve accurate enough results, and in the effort of reducing the number of instructions per second, this paper focuses on exploring the most adequate approximations for the activation function. The experimental work proves that the approximated neural network-based classifier achieves the same efficiency as that reached by exact networks (without these approximations), but, this is the crucial point, with the added advantage of extremely reducing the computational cost on digital signal processor.