Open Access
ARTICLE
Soft Computing Techniques for Classification of Voiced/Unvoiced Phonemes
Mohammed Algabria,c, Mohamed Abdelkader Bencherifc, Mansour Alsulaimanb,c, Ghulam Muhammadb, Mohamed Amine Mekhtichec
a Computer Science Department, King Saud University, Riyadh, Saudi Arabia;
b Computer Engineering Department, King Saud University, Riyadh, Saudi Arabia;
c Center of Smart Robotics Research (CS2R), King Saud University, Riyadh, Saudi Arabia
* Corresponding Author: Mohammed Algabri,
Intelligent Automation & Soft Computing 2018, 24(2), 267-274. https://doi.org/10.1080/10798587.2017.1278961
Abstract
A method that uses fuzzy logic to classify two simple speech features for the automatic classification
of voiced and unvoiced phonemes is proposed. In addition, two variants, in which soft computing
techniques are used to enhance the performance of fuzzy logic by tuning the parameters of the
membership functions, are also presented. The three methods, manually constructed fuzzy logic
(VUFL), fuzzy logic optimized with genetic algorithm (VUFL-GA), and fuzzy logic with optimized
particle swarm optimization (VUFL-PSO), are implemented and then evaluated using the TIMIT speech
corpus. Performance is evaluated using the TIMIT database in both clean and noisy environments. Four
different noise types from the AURORA database—babble, white, restaurant, and car noise—at six
different signal-to-noise ratios (SNRs) are used. In all cases, the optimized fuzzy logic methods (VUFLGA and VUFL-PSO) outperformed manual fuzzy logic (VUFL). The proposed method and variants are
suitable for applications featuring the presence of highly noisy environments. In addition, classification
accuracy by gender is also studied.
Keywords
Cite This Article
M. Algabri, M. A. Bencherif, M. Alsulaiman, G. Muhammad and M. A. Mekhtiche, "Soft computing techniques for classification of voiced/unvoiced phonemes,"
Intelligent Automation & Soft Computing, vol. 24, no.2, pp. 267–274, 2018. https://doi.org/10.1080/10798587.2017.1278961