Show simple item record

dc.contributor.authorKasabov, Nikolaen_NZ
dc.contributor.authorKilgour, Richarden_NZ
dc.contributor.authorSinclair, Stephenen_NZ
dc.date.available2011-04-07T03:05:37Z
dc.date.copyright1999-03en_NZ
dc.identifier.citationKasabov, N., Kilgour, R., & Sinclair, S. (1999). From hybrid adjustable neuro-fuzzy systems to adaptive connectionist-based systems for phoneme and word recognition (Information Science Discussion Papers Series No. 99/07). University of Otago. Retrieved from http://hdl.handle.net/10523/925en
dc.identifier.urihttp://hdl.handle.net/10523/925
dc.description.abstractThis paper discusses the problem of adaptation in automatic speech recognition systems (ASRS) and suggests several strategies for adaptation in a modular architecture for speech recognition. The architecture allows for adaptation at different levels of the recognition process, where modules can be adapted individually based on their performance and the performance of the whole system. Two realisations of this architecture are presented along with experimental results from small-scale experiments. The first realisation is a hybrid system for speaker-independent phoneme-based spoken word recognition, consisting of neural networks for recognising English phonemes and fuzzy systems for modelling acoustic and linguistic knowledge. This system is adjustable by additional training of individual neural network modules and tuning the fuzzy systems. The increased accuracy of the recognition through appropriate adjustment is also discussed. The second realisation of the architecture is a connectionist system that uses fuzzy neural networks FuNNs to accommodate both a prior linguistic knowledge and data from a speech corpus. A method for on-line adaptation of FuNNs is also presented.en_NZ
dc.format.mimetypeapplication/pdf
dc.publisherUniversity of Otagoen_NZ
dc.relation.ispartofseriesInformation Science Discussion Papers Seriesen_NZ
dc.subjectpattern recognitionen_NZ
dc.subjectartificial intelligenceen_NZ
dc.subjectneural networksen_NZ
dc.subjectspeech recognitionen_NZ
dc.subject.lcshQA76 Computer softwareen_NZ
dc.titleFrom hybrid adjustable neuro-fuzzy systems to adaptive connectionist-based systems for phoneme and word recognitionen_NZ
dc.typeDiscussion Paperen_NZ
dc.description.versionUnpublisheden_NZ
otago.bitstream.pages21en_NZ
otago.date.accession2010-12-15 19:38:01en_NZ
otago.schoolInformation Scienceen_NZ
otago.openaccessOpen
otago.place.publicationDunedin, New Zealanden_NZ
dc.identifier.eprints1020en_NZ
otago.school.eprintsKnowledge Engineering Laboratoryen_NZ
otago.school.eprintsInformation Scienceen_NZ
dc.description.references[1] S. Amari, N.K. Kasabov (Eds.), Brain-like Computing and Intelligent Information Systems, Springer, Berlin, 1997. [2] Clark, C. Yallop, An Introduction to Phonetics and Phonology, Blackwell, Cambridge MA, 1990. [3] Cole et al., The challenge of spoken language systems: research directions for the Nineties, IEEE Trans. Speech Audio Process. 3 (1) (1995) 1-21. [4] Li-Min Fu, Building expert systems on neural architectures, Proc. Ist IEEE Internat. Conf. on Artificial Neural Networks, 1989, pp. 221-225. [5] Goldberg, Genetic Algorithms in Search, Optimisation and Machine Learning, Addison-Wesley, New York, 1989. [6] Q. Huo, C.-H. Lee, A study of on-line Quasi-Bayes adaptation for CDHMM-based speech recognition, Proc. IEEE Internat. Conf. on Acoustic, Speech, and Signal Processing, 1996, pp. 705-708. [7] J.S.R. Jang, ANFIS: adaptive-network-based fuzzy inference system, IEEETrans. Systems Man Cybernet. 23 (3) (1993) 665-684. [8] N.K. 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, Lawrence Erlbaum, Hillsdale, NJ, 1995, pp. 178-185. [9] N.K. Kasabov, Hybrid connectionist fuzzy production systems - towards building comprehensive AI, Intell. Automat. Soft Comput. 1 (1995) 351-360. [10] N.K. Kasabov, Hybrid Connectionist Fuzzy Rule-based Systems for Speech Recognition, Lecture Notes in Computer Science/Artificial Intelligence, vol. 1011, Springer, Berlin, 1995, pp. 20-33. [11] N.K. Kasabov, Adaptable counectionist production systems, Neurocomputing 13 (1996) 95-117. [12] N.K. Kasabov, Foundations of Neural Networks, Fuzzy Systems and Knowledge Engineering, MIT Press, Cambridge, MA, 1996. [13] N.K. Kasabov, Learning and approximate reasoning in fuzzy neural networks and hybrid systems, Fuzzy Sets and Systems 82 (1996) 135-149. [14] N.K. Kasabov, Learning strategies for modular neuro-fuzzy systems: a case study on phoneme-based speech recognition, J. Intell. Fuzzy Systems 5 (1997) 1-10. [15] N.K. Kasabov, A framework for intelligent conscious machines and applications for adaptive speech recognition, in: Amari, N.K. Kasabov (Eds.), Brain-like Computing and Intelligent Systems, Springer, Berlin, 1997. [16] N.K. Kasabov, ECOS: Evolving connectionist systems - methods, algorithms, applications, in: Proc. ICONIP'98 Conf. (International Conference on Neuro-Information Processing), Kitakyushu, Japan, 21-23 October 1998, pp. 793-796. [17] N.K. Kasabov, J.S. Kim, M. Watts, A. Gray, FuNN/2 - a fuzzy neural network architecture for adaptive learning and knowledge acquisition, Inform. Sci. 101 (3-4) (1997) 155-175. [18] N.K. Kasabov, R. Kozma, M. Watts, Optimization and adaption of fuzzy neural networks through genetic algorithms and learning-with-forgetting methods and applications for phoneme based speech recognition, Inform. Sci. 110 (1998) 61-79. [19] N.K. Kasabov, E. Postma, J. van en Herik, AVIS: a connectionist framework for integrated audio and visual information processing systems, in: Proc. Iizuka'98 Conf., 16-20 October, Iizuka, Japan, 1998. [20] N.K. Kasabov, S.J. Sinclair, R. Kilgour, C. Watson, M. Laws, D. Kassabova, Intelligent human computer interfaces and the case study of building English-to-Māori talking dictionary, in: N.K. Kasabov, G. Coghill (Eds.), Proc. ANNES'95, Dunedin, IEEE Computer Society Press, Los Alamitos, 1995, pp. 294-297. [21] R.I, Kilgour, Hybrid fuzzy systems and neural networks for speech recognition, Unpublished Masters Thesis, University of Otago, 1996. [22] K. Kim, N. Relkin, K.-M. Lee, J. Hirsch, Distinct cortical areas associated with native and second languages, Nature 388 (1997) 171-174. [23] D. Massaro, Perceiving Talking Faces, MIT Press, Cambridge, MA, 1997. [24] D. Massaro, M. Cohen, Integration of visual and auditory information in speech perception, J. Experimental Psychol.: Human Perception Performance 9 (1983) 753-771. [25] Mitra, S. Pal, Fuzzy multi-layer perceptron, inferencing and rule generation, IEEE Trans. Neural Networks 6 (1995) 51-63. [26] Morgan, C. Scofield, Neural Networks and Speech Processing, Kluwer Academic Publishers, Amsterdam, 1991. [27] N. Pal, E. Kumar, Neural networks for dimensionality reduction, in: Kasabov et al. (Eds.), Connectionist Based Information Systems, Proc. ICONIP'97 Conf., Dunedin, Springer, Singapore, 1997, pp. 221-224. [28] R. Rabiner, Applications of voice processing to telecommunications, Proc. IEEE 82 (1994) 199-228. [29] D. Robinson, Artificial Intelligence and Expert Systems, McGraw Hill, New York, 1988. [30] G. Rummery, M. Niranjan, On-line Q-learning using connectionist systems, CUED/F-INFENG/TR 166, Cambridge University Engineering Department, 1994. [31] A. Sankar, L. Neumeyer, M. Weintraub, An experimental study of acoustic adaptation algorithms, Proc. IEEE Internat. Conf. on Acoustic, Speech, and Signal Processing, 1996, pp. 713-716. [32] M.A-S. Seyed, Bayesian and predictive techniques for speaker adaptation, Unpublished PhD Thesis, University of Cambridge, 1996. [33] S.J. Sinclair, Development of an isolated speech digit recognition system based on backpropagation neural networks, Unpublished Masters Thesis, University of Otago, 1996. [34] S.J. Sinclair, C. Watson, The development of the Otago speech database, in: N. Kasabov, G. Coghill (Eds.), Proc. ANNES '95, Dunedin, IEEE Computer Society Press, Los Alamitos, 1995, pp. 294-297. [35] T. Yamakawa, H. Kusanagi, E. Uchino, T. Miki, A new effective algorithm for neo fuzzy neuron model, in: Proc. 5th IFSA World Congress, 1993, pp. 1017-1020. [36] Yamazaki, Research activities on spontaneous speech, in: N. Kasabov, G. Coghill (Eds.), Proc. ANNES '95, Dunedin, IEEE Computer Society Press, Los Alamitos, 1995, pp. 280-283. [37] S. Young, Large vocabulary continuous speech recognition: a review, Internal Report, Cambridge University Engineering Department, 1996.en_NZ
otago.relation.number99/07en_NZ
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record