Authors:
Frejus A. A. Laleye
1
;
Eugene C. Ezin
2
and
Cina Motamed
3
Affiliations:
1
Institut de Mathématiques et de Sciences Physiques, Université d’Abomey-Calavi and Universit´e du Littoral Cˆote d’Opale, Benin
;
2
Institut de Mathématiques et de Sciences Physiques and Université d’Abomey-Calavi, Benin
;
3
Universit´e du Littoral Cˆote d’Opale, France
Keyword(s):
Decision Fusion, Fuzzy Logic, Deep Belief Networks, Phoneme Classification, Naive Bayes, LVQ, Fongbe Language.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Business Analytics
;
Cardiovascular Technologies
;
Computational Intelligence
;
Computing and Telecommunications in Cardiology
;
Data Engineering
;
Decision Support Systems
;
Decision Support Systems, Remote Data Analysis
;
Fuzzy Control
;
Fuzzy Systems
;
Health Engineering and Technology Applications
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Knowledge-Based Systems
;
Machine Learning in Control Applications
;
Neural Networks Based Control Systems
;
Soft Computing
;
Symbolic Systems
Abstract:
In this paper, we compare three approaches for decision fusion in a phoneme classification problem. We
especially deal with decision-level fusion from Naive Bayes and Learning Vector Quantization (LVQ) classifiers
that were trained and tested by three speech analysis techniques: Mel-frequency Cepstral Coefficients
(MFCC), Relative Spectral Transform - Perceptual Linear Prediction (Rasta-PLP) and Perceptual Linear Prediction
(PLP). Optimal decision making is performed with the non-parametric and parametric methods. We
investigated the performance of both decision methods with a third proposed approach using fuzzy logic. The
work discusses the classification of an African language phoneme namely Fongbe language and all experiments
were performed on its dataset. After classification and the decision fusion, the overall decision fusion
performance is obtained on test data with the proposed approach using fuzzy logic whose classification accuracies
are 95,54% for consonants and 8
3,97% for vowels despite the lower execution time of Deep Belief
Networks.
(More)