W
Walid Mahdi
Researcher at University of Sfax
Publications - 71
Citations - 683
Walid Mahdi is an academic researcher from University of Sfax. The author has contributed to research in topics: Feature extraction & Video tracking. The author has an hindex of 14, co-authored 67 publications receiving 531 citations. Previous affiliations of Walid Mahdi include University of Technology of Compiègne & Taif University.
Papers
More filters
Journal ArticleDOI
Improving speech recognition using data augmentation and acoustic model fusion
TL;DR: This work proposes a new Deep Neural Network (DNN) speech recognition architecture which takes advantage from both DA and EM approaches in order to improve the prediction accuracy of the system.
Posted Content
Lip Localization and Viseme Classification for Visual Speech Recognition
TL;DR: A new approach to automatically localize lip feature points in a speaker’s face and to carry out a spatial-temporal tracking of these points and the extracted visual information is classified in order to recognize the uttered viseme (visual phoneme).
Book ChapterDOI
A New Visual Speech Recognition Approach for RGB-D Cameras
TL;DR: The obtained recognition results demonstrate that lipreading can be performed effectively, and the proposed approach outperforms recent works in the literature for the speaker dependent setting while being competitive for theSpeaker independent setting.
Journal ArticleDOI
Deep multilayer multiple kernel learning
TL;DR: This paper proposes to optimize the network over an adaptive backpropagation MLMKL framework using the gradient ascent method instead of dual objective function, or the estimation of the leave-one-out error, and achieves high performance.
Journal ArticleDOI
Spatio-temporal features for the automatic control of driver drowsiness state and lack of concentration
Belhassen Akrout,Walid Mahdi +1 more
TL;DR: This work has proposed a fusion system for drowsiness detection based on blinking measurement and the 3D head pose estimation and shows the effectiveness of the suggested approach.