H
Hocine Bourouba
Researcher at Yahoo!
Publications - 17
Citations - 229
Hocine Bourouba is an academic researcher from Yahoo!. The author has contributed to research in topics: Support vector machine & Hidden Markov model. The author has an hindex of 7, co-authored 17 publications receiving 186 citations.
Papers
More filters
Journal ArticleDOI
Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals
TL;DR: A new feature extraction method based on empirical mode decomposition (EMD) is proposed, which decomposed the EEG signal into intrinsic mode functions (IMFs) by the EMD algorithm and four statistical parameters are calculated over these IMFs constituting the input feature vector to be fed to a multilayer perceptron neural network (MLPNN) classifier.
Proceedings ArticleDOI
A speech signal based gender identification system using four classifiers
TL;DR: Gaussian mixture model (GMM), multilayer perceptrons (MLP), vector quantization (VQ) and learning vector quantification (LVQ) are the classifiers used in this work along with mel frequency cepstral coefficients (MFCC) for gender identification.
Journal ArticleDOI
An Improved GMM-SVM System based on Distance Metric for Voice Pathology Detection
TL;DR: This work presents an efficient method for voice pathology detection based on speech signal proc essing and machine learning techniques and exploits the simi larity function of the RBF kernel to separate the GMM models representing norma l and pathological voices.
Proceedings ArticleDOI
New Hybrid System (Supervised Classifier/HMM) for Isolated Arabic Speech Recognition
TL;DR: This work is an alternative hybrid approach GHMM/supervised classifier (SVM or KNN) used in speech recognition using hidden Markov model with supervised classifier algorithm.
Journal Article
Robust Speech Recognition Using Perceptual Wavelet Denoising and Mel-frequency Product Spectrum Cepstral Coefficient Features
TL;DR: Robust Speech Recognition Using Perceptual Wavelet Denoising and Mel-frequency Product Spectrum Cepstral Coefficient Features is presented.