Adaptive Neuro-Fuzzy Black-Box Modeling Based on Instrumental Variable Evolving Algorithm

Rocha, Orlando; Serra, Ginalber Luiz de Oliveira

doi:10.1007/s40313-016-0285-8

Cited by 5 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extensive development of speech processing research demonstrates the effort to improve the performance of speech recognition systems for practical applications (Bellegarda and Monz 2016;Silva and Serra 2014). The use of such systems allows autonomy in areas as telephony, in which service requests are directed by voice commands (Cardoso et al 2010); in automotive engineering, by driving devices inside the cars (Qian et al 2009;Hua and Ng 2010;Li et al 2013); in computer systems, through computer utility programs, in addition to robotic application (Koo et al 2014) and in residential and hospital automation for accessibility of people with locomotive and visual disabilities (Gnanasekar et al 2012;Singh and Yadav 2015).…”

Section: Motivation and Justificationmentioning

confidence: 99%

Hierarchical Expert Neural Network System for Speech Recognition

Rocha

Silva

Barros

2019

J Control Autom Electr Syst

View full text Add to dashboard Cite

This work proposes a hierarchical architecture composed of a expert neural network set based on the ensemble method with dynamic selection of classifiers for application in speech recognition systems. Therefore, 30 commands in the Brazilian Portuguese language were coded by a two-dimensional time matrix, resulting from the application of the discrete cosine transformation in the mel-cepstral coefficients. These patterns were modified by means of a nonlinear transformation to a high-dimensionality space through a set of Gaussian radial basis functions (GRBFs) parameterized with the centroid and covariance characteristics of the classes. The classification was made through the dynamic classifier selection approach, in which multilayer perceptron and learning vector quantization configurations were analyzed to constitute the multiple classifiers specialized in the subdivisions made in the total of classes to be recognized. Then, given a new test pattern, the GRBF that presents the highest value of the receptive field in relation to the input feature vector indicates the class to which the pattern is nearer, thus directing to the expert neural network that provides the final result of classification based on the local accuracy.

show abstract