Automatic detection of articulations disorders from children's speech preliminary study

Automatic Detection of Articulations Disorders from children's speech is the major interest for the diagnosis and monitoring of articulations disorders therapy. In this work, acoustic features LPC (Linear prediction cepstrum) have been used with the two most commonly used classifier GMM-UBM (Gaussian mixture model-universal background model) and SVM (Support Vector Machines). We have used the idea of stacking the means of the GMM-UBM model to form a mean super vector and introduce the resulting super vector to SVM system. The main contribution of this paper is the used of automatic speaker recognition to detect the articulation disorder from the children speech and the investigation of the performance gained using a hybrid strategy between GMM-UBM and SVM systems. Series of experiments will be conducted; demonstrations of results from different experiments will be presented, tested and evaluated. Indeed we have found that this method is effective and robust.