Connectionist Probability Estimators in Hmm Using Genetic Clustering Application for Speech Recognition and Medical Diagnosis

The main goal of this paper is to compare the performance which can be achieved by five different approaches analyzing their applications’ potentiality on real world paradigms. We compare the performance obtained with (1) Multi-network RBF/LVQ structure (2) Discrete Hidden Markov Models (HMM) (3) Hybrid HMM/MLP system using a Multi LayerPerceptron (MLP) to estimate the HMM emission probabilities and using the Kmeans algorithm for pattern clustering (4) Hybrid HMM-MLP system using the Fuzzy C-Means (FCM) algorithm for fuzzy pattern clustering and (5) Hybrid HMM-MLP system using the Genetic Algorithm (AG) for genetic clustering. Experimental results on Arabic speech vocabulary and biomedical signals show significant decreases in error rates of hybrid HMM/MLP/AG pattern recognition in comparison to those of other research experiments by integrating three types of features (PLP, log-RASTA PLP, JRASTA PLP) were used to test the robustness of our hybrid recognizer in the presence of convolution and additive noise.