Home // ADVCOMP 2012, The Sixth International Conference on Advanced Engineering Computing and Applications in Sciences // View article

A Hybrid Method for Extraction of Low-Order Features for Speech Recognition Application

Authors:
Washington Silva
Ginalber Serra

Keywords: Discrete Cosine Transform; Speech Recognition; Fuzzy Systems; Genetic Algorithm.

Abstract:
The concept of fuzzy sets and fuzzy logic is} widely used in the proposal of several methods applied to systems modeling, classification and pattern recognition problem. This paper proposes a genetic-fuzzy system for extraction of low-order features for speech recognition application. In addition to pre-processing, with mel-cepstral coefficients, the Discrete Cosine Transform (DCT) is used to generate a two-dimensional time matrix with the features of low-order for each pattern to be recognized. A genetic algorithm is used to optimize a Mamdani fuzzy inference system in order to obtain the best model for final recognition. The proposed method used in this paper was named Hibrid Method for Extraction of Low-Order Features for Speech Recognition Application (HMFE). Experimental results for speech recognition applied to Brazilian language show the efficiency of the proposed methodology compared to methodologies widely used and cited in the literature.

Pages: 123 to 129

Copyright: Copyright (c) IARIA, 2012

Publication date: September 23, 2012

Published in: conference

ISSN: 2308-4499

ISBN: 978-1-61208-237-0

Location: Barcelona, Spain

Dates: from September 23, 2012 to September 28, 2012