Abstract
The paper presents a model for solving speech recognition tasks by exploring hybrid systems which include neural networks and fuzzy-rule based systems. The model utilises a set of neural networks for pattern recognition and a connectionist production system (CPS) for a higher level processing. Fuzzy rules for language processing are realised in the CPS. The whole process of speech recognition and language processing is considered to be one integrated process having two tightly coupled and interacting phases without a rigid, crisp border between them. The fuzziness and the ambiguity at the border line between the pattern matching and language understanding can be well represented in CPS. It facilitates flexible reasoning over fuzzy linguistic rules. An experiment on phonemes and digits recognition in English language is given for illustration. CPS make possible Connectionist implementation of the whole process of spoken language recognition both at low level and at a higher level. This brings all the benefits of the connectionist systems to the practical applications in the speech recognition area.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
W. Ainsworth. Speech Recognition By Machine, Peter Peregrinus Ltd, London, 1988.
R. Cole et al. The Challenge of Spoken Language Systems: Research Directions for the Nineties, IEEE Transactions on Speech and Audio Processing, vol.3, No.1, January 1995, pp. 1–21, 1995.
A.C. Gimson. An Introduction to the Pronunciation of English, Edward Arnould, 1989.
N. Kasabov, D. Nikovski, E. Peev. Speech recognition based on Kohonen Self Organizing Feature Maps and Hybrid Connectionist Systems, in: N. Kasabov (ed) Artificial Neural Networks and Expert Systems, IEEE Computer Society Press, Los Alamitos, pp. 113–117, 1993.
N. Kasabov and E.Peev. Phoneme Recognition with Hierarchical Self Organised Neural Networks and Fuzzy Systems, in: M.Marinaro and P.Morasso (eds) Proceedings of the ICANN'94, Springer Verlag, vol.1, pp.201–204, 1993.
N. Kasabov, S.Shishkov. A Connectionist Production System with a Partial Match and Its Use for Approximate Reasoning. Connection Science, vol.5, 3&4, pp.275–305, 1993.
N. Kasabov. Learning Fuzzy Production Rules for Approximate Reasoning with Connectionist Production Systems, in: S.Gielen and B. Kappen (Eds) Proceedings of the International Conference on Artificial Neural Networks ICANN'93, Amsterdam, September, pp.337–345, Springer Verlag, 1993.
N. Kasabov. Neural Networks, Fuzzy Systems and Knowledge Engineering, to be published, MIT Press, Cambridge, Massachussets, 550 pages.
N. Kasabov, C.Watson, S.Sinclair, R.Kilgour. Integrating neural networks and fuzzy systems for speech recognition, in: Proceedings of the Speech Science and Technology Conference SST-94, University of Western Australia, Perth, Australia, December, pp. 462–467, 1994.
N. Kasabov. Towards Using Hybrid Connectionist Fuzzy Production Systems for Speech Recognition, in: Proceedings of the 1994 IEEE/Nagoya University World Wise men/women Workshop on Fuzzy Logic and Neural Networks/Genetic Algorithms, Nagoya, Japan, August, pp. 9–13, 1994.
N. Kasabov. Building Comprehensive AI and the Task of Speech Recognition, in: J.Alspector, R.Goodman, T.Brown (eds) Applications of Neural Networks to Telecommunications, 2, Laurence Erlbaum, 1995, pp. 178–186.
N. Kasabov. Connectionist Fuzzy Production Systems. Lecture Notes In Computer Science/Artificial Intelligence, No.847, pp.114–132, 1994.
M. Maclagan. An Acoustic Study of New Zealand Vowels, New Zealand Speech Therapists' Journal, vol.37, No.1, May, pp.20–26, 1982.
S. Mitra and S. Pal. Fuzzy Multi-Layer Perceptron, Inferencing and Rule Generation, IEEE Transactions on Neural Networks, vol.6. No. 1, January, pp.51–63, 1995.
D. Morgan and C.Scofield. Neural Networks and Speech Processing, Kluwer Academic Publishers, 1991.
M. Mukaidono, M. Yamaoka. A Learning Method of Fuzzy Inference Rules with Neural Networks and its Application, in: Proceedings of the 2nd International Conference on Fuzzy Logic & Neural Networks, Iizuka, Japan, 1992, pp.185–187, 1992.
K. Nakamura, T.Fujimaki, R. Horikawa, Y.Ageishi: Fuzzy Network Production System. In: Proceedings of the 2nd International Conference on Fuzzy Logic & Neural Networks, Iizuka, Japan, 1992, pp. 127–130.
F.J. Owens. Signal Processing of Speech, MacMillan, 1994.
D. Pallet et al. Benchmark tests for the DARPA spoken language program, in: DARPA Workshop Speech, Natural Language Processing, March, 1993.
L. R. Rabiner. Applications of Voice Processing to Telecommunications, Proceedings of the IEEE, vol 82, No. 2, Feb, p199–228, 1994.
D.B. Roe and J.G.Wilpon. Whither Speech Recognition: The Next 25 Years, IEEE Communications Magazine, November, pp.54–62, 1993.
H. Sawai, A. Waibel, P. Haffner, M. Miyatake, and K. Shikano. Parallelism, Hierarchy, Scaling in Time-Delay Neural Networks for Spotting Japanese Phonemes/CV-Syllables, in: Proceedings of IJCANN '89, vol. 2, pp. 81–88, 1989.
T. Terano, K.Asai, M.Sugeno. Fuzzy Systems — Theory and Applications, Academic Press, 1992.
K. Unnikrishnan, Hopfield, J.J. and Tank, D.W.. Connected-Digit Speaker-Dependant Speech Recognition with Time-Delayed Connections. IEEE Transactions on Signal Processing, 39, 698–713, 1989.
A. Waibel, T. Hanazawa, Hinton, G., Shikano, K. and K.J.Lang. Phoneme Recognition Using Time-Delay Neural Networks. IEEE Transactions on Acoustics, Speech and Signal Processing, 37, pp. 328–339, 1989.
A. Waibel. Consonant Recognition by Modular Construction of Large Phonemic Time-Delay Neural Networks. In: D.Touretzky (ed.) Advances in Neural Information Processing 1. San Mateo, CA: Morgan Kaufmann, 1989.
Workshop on Fuzzy Database Systems and Information Retrieval, Proceedings of the FUZZ-IEEE/IFES'95 Conference, Yokohama, Japan, March 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kasabov, N.K. (1995). Hybrid connectionist fuzzy systems for speech recognition and the use of connectionist production systems. In: Furuhashi, T. (eds) Advances in Fuzzy Logic, Neural Networks and Genetic Algorithms. WWW 1994. Lecture Notes in Computer Science, vol 1011. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60607-6_2
Download citation
DOI: https://doi.org/10.1007/3-540-60607-6_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60607-9
Online ISBN: 978-3-540-48457-8
eBook Packages: Springer Book Archive