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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Deroo, O., Riis, C., Malfrere, F., Leich, H., Dupont, S., Fontaine, V., BoÎte, J.M.: Hybrid HMM/ANN system for speaker independent continuous speech recognition in French. Thesis, Faculté polytechnique de Mons – TCTS, BELGIUM (1997)
Bourlard, H., Dupont, S.: Sub-band-based speech recognition. In: Proc. IEEE International Conf. Acoustic, Speech and Signal Process, Munich, pp. 1251–1254 (1997)
Berthommier, F., Glotin, H.: A new SNR-feature mapping for robust multi-stream speech recognition. In: Proceeding of International Congress on Phonetic Sciences (ICPhS), Sanfrancisco, vol. XIV, pp. 711–715. University of California, Berkeley (1999)
Boite, J.-M., Bourlard, H., D’Hoore, B., Accaino, S., Vantieghem, J.: Task independent and dependent training: performance comparison of HMM and hybrid HMM/MLP approaches, vol. I, pp. 617–620. IEEE, Los Alamitos (1994)
Bezdek, J.C., Keller, J., Krishnapwam, R., Pal, N.R.: Fuzzy models and algorithms for pattern recognition and image processing. Kluwer, Boston (1999)
Hermansky, H., Morgan, N.: RASTA Processing of speech. IEEE Trans. on Speech and Audio Processing 2(4), 578–589 (1994)
Hagen, A., Morris, A.: Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASR. To appear in International Conference on Spoken Language Processing, Beijing (2000)
Hagen, A., Morris, A.: From multi-band full combination to multi-stream full combination processing in robust ASR. To appear in ISCA Tutorial Research Workshop ASR2000, Paris, France (2000)
Lazli, L., Sellami, M.: Hybrid HMM-MLP system based on fuzzy logic for arabic speech recognition. In: PRIS2003, The Third International Workshop on Pattern Recognition in Information Systems, Angers, France, April 22-23, pp. 150–155 (2003)
Lazli, L., Sellami, M.: Connectionist Probability Estimators in HMM Speech Recognition using Fuzzy Logic. In: Perner, P., Rosenfeld, A. (eds.) MLDM 2003. LNCS, vol. 2734, Springer, Heidelberg (2003)
Lazli, L., Chebira, A.-N., Madani, K.: Hidden Markov Models for Complex Pattern Classification. In: Ninth International Conference on Pattern Recognition and Information Processing, PRIP 2007, Minsk, Belarus, May 22-24 (2007), http://uiip.bas-net.by/conf/prip2007/prip2007.php-id=200.htm
Lazli, L., Chebira, A.-N., Laskri, M.-T., Madani, K.: Using hidden Markov models for classification of potentials evoked auditory. In: Conférence maghrébine sur les technologies de l’information, MCSEAI 2008, Ustmb, Oran, Algeria, April 28-30, pp. 477–480 (2008)
Pham, D.-L., Prince, J.-L.: An Adaptive Fuzzy C-means algorithm for Image Segmentation in the presence of Intensity In homogeneities. Pattern Recognition Letters 20(1), 57–68 (1999)
Riis, S.-K., Krogh, A.: Hidden Neural Networks: A framework for HMM-NN hybrids. In: IEEE 1997, to appear in Proc. ICASSP 1997, Munich, Germany, April 21-24 (1997)
Timm, H.: Fuzzy Cluster Analysis of Classified Data. IFSA/Nafips, Vancouver (2001)
Motsh, J.-F.: La dynamique temporelle du trons cérébral: Recueil, extraction et analyse optimale des potentiels évoqués auditifs du tronc cérébral Thesis, University of Créteil Paris XII (1987)
Dujardin, A.-S.: Pertinence d’une approche hybride multi-neuronale dans la résolution de problèmes liés au diagnostic industrièle ou médical. Internal report, I2S laboratory, IUT of "Sénart Fontainebleau, University of Paris XII, Avenue Pierre Point, 77127 Lieusaint, France (2006)
Morris, A., Hagen, A., Glotin, H., Bourlard, H.: Multi-stream adaptative evidence combination for noise robust ASR. Accepted for publication in Speech Communication (2000)
Morris, A., Hagen, A., Bourlard, H.: MAP combination of multi-stream HMM or HMM/ANN experts. Accepted for publication in Euro-speech 2001, Special Event Noise Robust Recognition, Aalborg, Denmark (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lazli, L., Chebira, A., Laskri, M.T., Madani, K. (2011). Hybrid HMM/ANN System Using Fuzzy Clustering for Speech and Medical Pattern Recognition. In: Cherifi, H., Zain, J.M., El-Qawasmeh, E. (eds) Digital Information and Communication Technology and Its Applications. DICTAP 2011. Communications in Computer and Information Science, vol 167. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22027-2_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-22027-2_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22026-5
Online ISBN: 978-3-642-22027-2
eBook Packages: Computer ScienceComputer Science (R0)