Using a New Hybrid Models for Speech and Medical Pattern Classification

Using a New Hybrid Models for Speech and Medical Pattern Classification International Journal of Computational Linguistics Research Lilia Lazli, Mounir Boukadoum, Abdennasser Chebira, Kurosh Madani 3 1 2012 http://www.dline.info/jcl/fulltext/v3n1/2.pdf The main goal of this paper is to compare the performance which can be achieved by two different hybrid approaches analyzing their applicationsâ€™ potentiality on real world paradigms (speech recognition and medical diagnosis). We compare the performance obtained with (1) Multinetwork RBF/LVQ structure, we use involves Learning Vector Quantization (LVQ) as a competitive decision processor and Radial Basis Function (RBF) neural models is used as classifier. (2) Hybrid HMM/MLP system using a Multi Layer-Perceptron (MLP) to estimate the Hidden Markov Models (HMM) emission probabilities.