Hybrid HMM/ANN System Using Fuzzy Clustering for Speech and Medical Pattern Recognition

Lilia Lazli,Abdennasser Chebira,Kurosh Madani,Mohamed Tayeb Laskri

doi:10.1007/978-3-642-22027-2_46

Hybrid HMM/ANN System Using Fuzzy Clustering for Speech and Medical Pattern Recognition

Lilia Lazli, Abdennasser Chebira + Show 2 more

https://doi.org/10.1007/978-3-642-22027-2_46

Copy DOI

Publication Date: Jan 1, 2011

Citations: 2

Affiliation: Badji Mokhtar University, University of Paris-Est

#Discrete Hidden Markov Models #Real World Paradigms + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

The main goal of this paper is to compare the performance which can be achieved by three different approaches analyzing their applications’ potentiality on real world paradigms. We compare the performance obtained with (1) Discrete Hidden Markov Models (HMM) (2) Hybrid HMM/MLP system using a Multi Layer-Perceptron (MLP) to estimate the HMM emission probabilities and using the K-means algorithm for pattern clustering (3) Hybrid HMM-MLP system using the Fuzzy C-Means (FCM) algorithm for fuzzy pattern clustering.Experimental results on Arabic speech vocabulary and biomedical signals show significant decreases in error rates for the hybrid HMM/MLP system based fuzzy clustering (application of FCM algorithm) in comparison to a baseline system.

Full Text