An Empirical Comparison of SVM and Some Supervised Learning Algorithms for Vowel recognition
Computation and Language
2015-07-23 v1 Machine Learning
Abstract
In this article, we conduct a study on the performance of some supervised learning algorithms for vowel recognition. This study aims to compare the accuracy of each algorithm. Thus, we present an empirical comparison between five supervised learning classifiers and two combined classifiers: SVM, KNN, Naive Bayes, Quadratic Bayes Normal (QDC) and Nearst Mean. Those algorithms were tested for vowel recognition using TIMIT Corpus and Mel-frequency cepstral coefficients (MFCCs).
Keywords
Cite
@article{arxiv.1507.06021,
title = {An Empirical Comparison of SVM and Some Supervised Learning Algorithms for Vowel recognition},
author = {Rimah Amami and Dorra Ben Ayed and Noureddine Ellouze},
journal= {arXiv preprint arXiv:1507.06021},
year = {2015}
}
Comments
08 pages