Abstract
Spoken languages evolve in the human brain through incremental learning, and this process can be modelled to a certain degree with the use of evolving connectionist systems. Several assumptions are hypothesised and proven through simulation in this chapter:
-
(a)
The learning system evolves its own representation of spoken language categories (phonemes) in an unsupervised mode by adjusting its structure to continuously flowing examples of spoken words (a learner does not know in advance which phonemes are going to be in a language, nor, for any given word, how many phoneme segments it has).
-
(b)
Learning words and phrases is associated with supervised presentation of meaning.
-
(c)
It is possible to build a “lifelong” learning system that acquires spoken languages in an effective way, possibly faster than humans, provided there are fast machines to implement the evolving learning models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Further Reading
Abdulla, W. H. and Kasabov, N. K. (2000) Feature selection for parallel CHMM speech recognition systems. In Proc. Fifth Joint Conference on Information Science, Vol. 2, pp. 874–878.
Laws, M. (2001) Information technology in the Maori context. PhD Thesis, University of Otago, New Zealand.
Kilgour, R. (2002) Evolving connectionist systems for phoneme-based speech recognition. PhD Thesis, University of Otago, New Zealand.
Segalowitz, S. J. (1983) Language Functions and Brain Organization. Academic Press, New York.
Seidenberg, M. (1997) Language acquisition and use: learning and applying probabilistic constraints. Science, 275, 1599–1603.
Tavazoie, S., Hughes, J. D., Campbell, M. J., Cho, R. J. and Church, G. M. (1999) Systematic determination of genetic network architecture. Nature Genetics, 22, 281–285.
Chomsky, N. (1995) The Minimalist Program. MIT Press, Cambridge, MA.
Elman, J., Bates, E., Johnson, M., Karmiloff-Smith, A., Parisi, D. and Plunkett, K. (1997) Rethinking Innateness (A Connectionist Perspective of Development). MIT Press, Cambridge, MA.
Lakoff, G. and Johnson, M. (1999) Philosophy in the Flesh. Basic Books, New York.
Plunkett, K. (1996) Connectionist approaches to language acquisition. In The Handbook of Child Language (eds. P. Fletcher and B. MacWhinney ). Blackwell, Oxford, pp. 36–72.
Jusczyk, P. (1997) The Discovery of Spoken Language. MIT Press, Cambridge, MA.
Snow, C. and Ferguson, C. (1977) Talking to Children: Language Input and Language Acquisition. Cambridge University Press, Cambridge.
Brent, M. (1997) Advances in the computational study of language acquisition. In Computational Approaches to Language Acquisition (ed. M. Brent ). MIT Press, Cambridge, MA.
Culicover, P. (1999) Syntactic Nuts: Hard Cases, Syntactic Theory, and Language Acquisition. Oxford University Press, Oxford.
Deacon, T. (1988) Human brain evolution: evolution of language circuits. In NATO ASI Series Intelligence and Evolutionary Biology (eds. H. Jerison and 1. Jerison). Springer-Verlag, Berlin.
Pinker, S. (1994) The Language Instinct: How the Mind Creates Language. Penguin, London.
Elman, J., Bates, E., Johnson, M., Karmiloff-Smith, A., Parisi, D. and Plunkett, K. (1997) Rethinking Innateness (A Connectionist Perspective of Development). MIT Press, Cambridge, MA.
Regier, T. (1996) The Human Semantic Potential: Spatial Language and Constrained Connectionism. MIT Press, Cambridge, MA.
Kilgour, R. (2002) Evolving connectionist systems for phoneme-based speech recognition. PhD Thesis, University of Otago, New Zealand.
Laws, M. (2001) Information technology in the Maori context. PhD Thesis, University of Otago, New Zealand.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag London
About this chapter
Cite this chapter
Kasabov, N. (2003). Modelling the Emergence of Acoustic Segments (Phonemes) in Spoken Languages. In: Evolving Connectionist Systems. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-3740-5_10
Download citation
DOI: https://doi.org/10.1007/978-1-4471-3740-5_10
Publisher Name: Springer, London
Print ISBN: 978-1-85233-400-0
Online ISBN: 978-1-4471-3740-5
eBook Packages: Springer Book Archive