A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids
×
Cite This
Citation & Abstract
E. Alexandre, L. Álvarez, L. Cuadra, M. Rosa-Zurera, and R. Vicen-Bueno, "A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids," Paper 7421, (2008 May.). doi:
E. Alexandre, L. Álvarez, L. Cuadra, M. Rosa-Zurera, and R. Vicen-Bueno, "A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids," Paper 7421, (2008 May.). doi:
Abstract: Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. This paper explores the feasibility of using a constructive algorithm for multilayer perceptrons (MLPs) applied to the problem of speech/non-speech classification in hearing aids. When properly designed and trained, MLPs are able to generate an arbitrary classification frontier with a relatively low computational complexity. The paper will focus on the design of a constructive algorithm for MLPs which attempts to converge to the minimum complexity network for the given problem. The results obtained will be compared with those cases in which the constructive algorithm
is not considered.
@article{alexandre2008a,
author={alexandre, enrique and álvarez, lorena and cuadra, lucas and rosa-zurera, manuel and vicen-bueno, raúl},
journal={journal of the audio engineering society},
title={a constructive algorithm for multilayer perceptrons for speech/non-speech classification in hearing aids},
year={2008},
volume={},
number={},
pages={},
doi={},
month={may},}
@article{alexandre2008a,
author={alexandre, enrique and álvarez, lorena and cuadra, lucas and rosa-zurera, manuel and vicen-bueno, raúl},
journal={journal of the audio engineering society},
title={a constructive algorithm for multilayer perceptrons for speech/non-speech classification in hearing aids},
year={2008},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. this paper explores the feasibility of using a constructive algorithm for multilayer perceptrons (mlps) applied to the problem of speech/non-speech classification in hearing aids. when properly designed and trained, mlps are able to generate an arbitrary classification frontier with a relatively low computational complexity. the paper will focus on the design of a constructive algorithm for mlps which attempts to converge to the minimum complexity network for the given problem. the results obtained will be compared with those cases in which the constructive algorithm
is not considered.},}
TY - paper
TI - A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids
SP -
EP -
AU - Alexandre, Enrique
AU - Álvarez, Lorena
AU - Cuadra, Lucas
AU - Rosa-Zurera, Manuel
AU - Vicen-Bueno, Raúl
PY - 2008
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2008
TY - paper
TI - A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids
SP -
EP -
AU - Alexandre, Enrique
AU - Álvarez, Lorena
AU - Cuadra, Lucas
AU - Rosa-Zurera, Manuel
AU - Vicen-Bueno, Raúl
PY - 2008
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2008
AB - Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. This paper explores the feasibility of using a constructive algorithm for multilayer perceptrons (MLPs) applied to the problem of speech/non-speech classification in hearing aids. When properly designed and trained, MLPs are able to generate an arbitrary classification frontier with a relatively low computational complexity. The paper will focus on the design of a constructive algorithm for MLPs which attempts to converge to the minimum complexity network for the given problem. The results obtained will be compared with those cases in which the constructive algorithm
is not considered.
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. This paper explores the feasibility of using a constructive algorithm for multilayer perceptrons (MLPs) applied to the problem of speech/non-speech classification in hearing aids. When properly designed and trained, MLPs are able to generate an arbitrary classification frontier with a relatively low computational complexity. The paper will focus on the design of a constructive algorithm for MLPs which attempts to converge to the minimum complexity network for the given problem. The results obtained will be compared with those cases in which the constructive algorithm
is not considered.
Authors:
Alexandre, Enrique; Álvarez, Lorena; Cuadra, Lucas; Rosa-Zurera, Manuel; Vicen-Bueno, Raúl
Affiliation:
Universidad de Alcalá
AES Convention:
124 (May 2008)
Paper Number:
7421
Publication Date:
May 1, 2008Import into BibTeX
Subject:
Analysis and Synthesis of Sound
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=14551