A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids

Alexandre E, Álvarez L, Cuadra L, Rosa-Zurera M, Vicen-Bueno R. A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids. In: AES Convention 124. Audio Engineering Society; 2008. Paper 7421. Available from: https://aes.org/publications/elibrary-page/?id=14551

@inproceedings{Alexandre2008_14551,
  author = {Alexandre, Enrique and Álvarez, Lorena and Cuadra, Lucas and Rosa-Zurera, Manuel and Vicen-Bueno, Raúl},
  title = {{A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids}},
  booktitle = {AES Convention 124},
  note = {Paper 7421},
  year = {2008},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14551}
}

TY  - CPAPER
TI  - A Constructive Algorithm for Multilayer Perceptrons for Speech/Non-Speech Classification in Hearing Aids
AU  - Alexandre, Enrique
AU  - Álvarez, Lorena
AU  - Cuadra, Lucas
AU  - Rosa-Zurera, Manuel
AU  - Vicen-Bueno, Raúl
T2  - AES Convention 124
M1  - Paper 7421
PY  - 2008
DA  - 2008/05/06
UR  - https://aes.org/publications/elibrary-page/?id=14551
PB  - Audio Engineering Society
LA  - en
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.
ER  -