M
Mohamed Mbarki
Researcher at University of Sousse
Publications - 29
Citations - 368
Mohamed Mbarki is an academic researcher from University of Sousse. The author has contributed to research in topics: Chemistry & Argumentation theory. The author has an hindex of 9, co-authored 19 publications receiving 222 citations. Previous affiliations of Mohamed Mbarki include Laval University.
Papers
More filters
Book ChapterDOI
Automatic Speech Emotion Recognition Using Machine Learning
Leila Kerkeni,Youssef Serrestou,Mohamed Mbarki,Kosai Raoof,Mohamed Ali Mahjoub,Catherine Cléder +5 more
TL;DR: This study shows that for Berlin database all classifiers achieve an accuracy of 83% when a speaker normalization (SN) and a feature selection are applied to the features, and for Spanish database, the best accuracy is achieved by RNN classifier without SN and with FS.
Journal ArticleDOI
Automatic speech emotion recognition using an optimal combination of features based on EMD-TKEO
Leila Kerkeni,Leila Kerkeni,Youssef Serrestou,Kosai Raoof,Mohamed Mbarki,Mohamed Ali Mahjoub,Catherine Cléder +6 more
TL;DR: A global approach for speech emotion recognition (SER) system using empirical mode decomposition (EMD) is proposed and a combination of all features extracted from the IMFs enhances the performance of the SER system and achieving 91.16% recognition rate.
Journal ArticleDOI
Toward Leveraging Smart Logistics Collaboration with a Multi-Agent System Based Solution
TL;DR: A multi-agent based solution where the architecture of each agent includes concurrent individual and collective Belief-Desire-Intension (BDI) structures to support and balance self and collaborative objectives is proposed.
Proceedings ArticleDOI
Speech Emotion Recognition: Methods and Cases Study.
TL;DR: The overall experimental results reveal that the feature combination of MFCC and MS has the highest accuracy rate on both Spanish emotional database using RNN classifier and Berlin emotional databaseUsing MLR 82,41%.
Journal ArticleDOI
MOONGA: Multi-Objective Optimization of Wireless Network Approach Based on Genetic Algorithm
TL;DR: This article proposes a new approach to optimizing the problem of node placement, based on the multi-objective genetic algorithm and the weighted sum optimization method, which it is called MOONGA (multi-objectives wireless network optimization using the genetic algorithm).