Nacereddine Hammami

Learn More
This paper introduces a fast learning method for a graphical probabilistic model for discrete speech recognition based on spoken Arabic digit recognition by means of a new proposed spanning tree structure that takes advantage of the temporal nature of speech signal. The experimental results obtained on a spoken Arabic digit dataset confirmed that for the(More)
Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in many speech and speaker recognition applications. In this paper, we study the effect of the second-order derivatives of MFCC on the recognition of the Spoken Arabic digits. The system was developed using the Hidden Markov Models (HMMs) and Tree distribution(More)
In this work we propose a novel method for automatic discrete speech recognition composed from two steps. In a first step, discrete speech features are extracted by means of Mel Frequency Cepstral Coefficients (MFCCs) followed by vector quantization (VQ). Then in a second step, the obtained features are fed to a Tree distribution classifier which provides(More)
This paper presents automatic recognition of the Spoken Arabic Digits recognition by means of preselected parameters for the Hidden Markov Models using the cross validation method. The experimental results give the best result with the obtained parameters, achieve 94.09% correct digit recognition dataset and confirm the promising capabilities of the(More)
The spread of many infectious diseases recently has necessitated the need to monitor them. Therefore, we present an idea for developing an web-based analysis system that will be able to regularly collect news reports from Arabic newspaper websites, and then be able to extract information relating to disease outbreaks, e.g. disease name, date and location.(More)
In light of the scarcity of both published and free Acoustic Arabic databases, we propose in this paper Acoustic Arabic database to be a reference in the field of automatic Arabic speech recognition, this database is the result of a case study that has been developed to contribute to the automatic diagnosis of speech disorders in Arabic speaking children,(More)
In this paper, we investigate a new joint statistical model for text classification, which is copula functions, that is a way of formalizing dependence structures of random vectors. A copula is a distribution function with the implicit capacity to model nonlinear dependencies. Copula have been widely used in economics and finance and more recently it has(More)