Malika Boudraa
University of Science and Technology Houari Boumediene
49 Papers
140 Citations
Malika Boudraa is an academic researcher from University of Science and Technology Houari Boumediene. The author has contributed to research in topics: Computer science & Hidden Markov model. The author has an hindex of 10, co-authored 45 publications.
Chat about Author
Papers
Digital fractional order differentiation-based algorithm for P and T-waves detection and delineation
TL;DR: Tests of the algorithm on ECG signals taken from the Massachusetts Institute of Technology/Beth Israel Hospital (MIT/BIH) database prove its capability to detect and delineate P-waves and T-waves in noisy ECG as well as low amplitude P-wave and inverted T-wave.
61
Automatic Crack Detection and Characterization During Ultrasonic Inspection
TL;DR: In this article, a method that avoids the image formation, replacing it with a sparse matrix (as there is no reason to store and operate on an excessive number of zeros), and automates crack detection by analyzing the curve formed by the sparse matrix elements.
54
Fully automated speaker identification and intelligibility assessment in dysarthria disease using auditory knowledge
TL;DR: This paper proposes an automatic speaker recognition approach especially adapted to identify dysarthric speakers and a method for the automatic assessment of the dysarthria severity level, and presents new approaches to improve the analysis and classification of disordered speech.
54
Voice disorder classification using speech enhancement and deep learning models
TL;DR: In this paper , a two-stage framework is proposed to perform an accurate classification of diverse voice pathologies, which considers impaired voice as a noisy signal and uses the noise lestral harmonic-to-noise ratio (CHNR) to put this hypothesis into practice, the second stage consists of a CNN-LSTM architecture designed to learn complex features from spectrograms of the first-stage enhanced signals.
37
Deep neural network architectures for dysarthric speech analysis and recognition
TL;DR: Experimental results show that the CNN-based system using perceptual linear prediction features provides a recognition rate that can reach 82%, which constitutes relative improvement of 11% and 32% when compared to the performance of LSTM- and GMM-HMM-based systems, respectively.
30