Hybrid Fuzzy HMM System for Arabic Connectionist Speech Recognition

In this paper, a new Arabic connectionist speech recognition system is presented. This recognition system is based on the combination of the fuzzy integral theory and hidden Markov model (HMM). In this context, the fuzzy integral is used to relax the independence assumptions that are necessary with probability functions. It was found that one particular case with the choice of fuzzy integral as the Choquet integral, fuzzy probability measure, and fuzzy intersection operator as multiplication, reduces the generalized fuzzy HMM to the classical HMM. The traditional HMM and the proposed fuzzy HMM systems are implemented by computer simulation and a performance comparison is carried out using the CSLU toolkit. The CSLU toolkit is a research and development software environment that provides a powerful and flexible tool for research in the field of spoken language understanding. It is noticed that, there is some improvements in recognition accuracy in case of the fuzzy HMM (FHMM) system over the classical HMM recognition system. The FHMM recognition system accuracy varies from 93.36% to 98.36% depending on the data set used whereas the classical HMM' accuracy varies from 91.27% to 94.60% for the same data sets

[1]  George J. Klir,et al.  Fuzzy sets and fuzzy logic - theory and applications , 1995 .

[2]  Tolga M. Duman,et al.  Noise predictive belief propagation , 2005, IEEE Transactions on Magnetics.

[3]  Paul D. Gader,et al.  Generalized hidden Markov models. I. Theoretical frameworks , 2000, IEEE Trans. Fuzzy Syst..

[4]  Johan Schalkwyk,et al.  CSLU-HMM: The CSLU Hidden Markov Modeling Environment , 2000 .

[5]  Mokhtar Sellami,et al.  Combination of vector quantization and hidden Markov models for Arabic speech recognition , 2001, Proceedings ACS/IEEE International Conference on Computer Systems and Applications.

[6]  Paul D. Gader,et al.  Generalized hidden Markov models. II. Application to handwritten word recognition , 2000, IEEE Trans. Fuzzy Syst..

[7]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[8]  Jian Zhang,et al.  Analysis of lip geometric features for audio-visual speech recognition , 2004, IEEE Trans. Syst. Man Cybern. Part A.

[9]  Kuntal Sengupta,et al.  Use of a novel generalized fuzzy hidden Markov model for speech recognition , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[10]  Michio Sugeno,et al.  Fuzzy Measure and Fuzzy Integral , 1972 .

[11]  Lawrence R. Rabiner,et al.  A tutorial on Hidden Markov Models , 1986 .

[12]  Peng-Yung Woo,et al.  Fuzzy speech recognition , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).