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

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.

[1]  Hervé Bourlard,et al.  MAP combination of multi-stream HMM or HMM/ANN experts , 2001, INTERSPEECH.

[2]  Andrew C. Morris,et al.  Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASR , 2000, INTERSPEECH.

[3]  Hervé Bourlard,et al.  Subband-based speech recognition , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  James M. Keller,et al.  Fuzzy Models and Algorithms for Pattern Recognition and Image Processing , 1999 .

[5]  Anders Krogh,et al.  Hidden neural networks: a framework for HMM/NN hybrids , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Hervé Bourlard,et al.  From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR , 2000 .

[7]  Mokhtar Sellami,et al.  Connectionist Probability Estimators in HMM Arabic Speech Recognition Using Fuzzy Logic , 2003, MLDM.

[8]  H. Timm,et al.  Fuzzy cluster analysis of classified data , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[9]  Mokhtar Sellami,et al.  Hybrid HMM-MLP System based on Fuzzy Logic for Arabic Speech Recognition , 2003, PRIS.

[10]  Hervé Glotin,et al.  Multi-stream adaptive evidence combination for noise robust ASR , 2001, Speech Commun..

[11]  Hervé Bourlard,et al.  Task independent and dependent training: performance comparison of HMM and hybrid HMM/MLP approaches , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Hynek Hermansky,et al.  RASTA processing of speech , 1994, IEEE Trans. Speech Audio Process..

[13]  Jean-François Motsch.  La dynamique temporelle du tronc cérébral : recueil, extraction et analyse optimale des potentiels évoqués auditifs du tronc cérébral , 1987 .