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.
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, 2008
Subject: Analysis and Synthesis of Sound
No AES members have commented on this paper yet.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.