Abstract
The adaptation to the changes of environment is crucial to improve automatic speech recognition systems’ robustness in various conditions of use. We investigate the adaptation of such systems using evolutionary algorithms. Our systems are based on neural networks. Their adaptation abilities rely on their capacity to learn and to evolve. Within the framework of this work, we study both main methods concerning hybridization of training and evolution, namely the Lamarckian and Darwinian evolution. We show that the knowledge inheritance of a generation to another is much faster and more powerful for the adaptation to a set of acoustic environments changes.
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.
References
Allen, J.B., Berkley, D.A.: Image Method for efficiently simulating small-room acoustics. JASA 65(4), 943–950 (1979)
Bäck, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press, New York (1996)
Bourlard, H.: Reconnaissance Automatique de la Parole: Modélisation ou Description? In: XXIemes Journées d’Etude sur la Parole(JEP 1996), Avignon, France, pp. 263–272 (1996)
Cobb, H.G., Grefenstette, J.J.: Genetic Algorithms for Tracking Changing Environments. In: International Conference on Genetic Algorithms, Fifth International Conference on Genetic Algorithms (ICGA 1993), pp. 523–530. Morgan Kaufmann, San Francisco (1993)
Hermansky, H.: Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of Acoustic Society Am. 87(4), 1738–1752 (1990)
Junqua, J.C., Haton, H.: Robustness in Automatic Speech Recognition. Ed Kluwer Academic Publisher, Dordrecht (1996)
Kabré, H., Spalanzani, A.: EVERA: A system for the Modeling and Simulation of Complex Systems. In: Proceedings of the First International Workshop on Frontiers in Evolutionary Algorithms, FEA 1997, North Carolina, pp. 184–188 (1997)
Mayley, G.: Landscapes, Learning Costs and Genetic Assimilation. Special Issue of Evolutionary Computation on the Baldwin Effect 4(3) (1996)
Mori, N., Kita, H., Nishikawa, Y.: Adaptation to a Changing Environment by Means of the Thermodynamical Genetic Algorithm. In: 4th Conference on Parallel Problem Solving from Nature, Berlin, Germany (1996)
Nolfi, S., Elman, J.L., Parisi, D.: Learning and Evolution in Neural Networks. Technical Report 94-08, Department of Neural Systems and Artificial Life, Rome, Italy (1994)
Nolfi, S., Parisi, D.: Learning to Adapt to Changing Environments in Evolving Neural Networks. Technical Report 95-15, C.N.R. de Rome, Italy (1996)
Sasaki, T., Tokoro, M.: Adaptation toward Changing Environments: Why Darwinian in Nature? In: Fourth European Conference on Artificial Life (1997)
Spalanzani, A., Kabré, H.: Evolution, Learning and Speech Recognition in Changing Acoustic Environments. In: 5th Conference on Parallel Problem Solving from Nature, pp. 663–671. Springer, Amsterdam (1998)
Spalanzani, A., Selouani, S.-A., Kabré, H.: Evolutionary Algorithms for Optimizing Speech Data Projection. In: GECCO 1999, Orlando (1999)
Turney, P., Whitley, D., Anderson, R.: Evolution, Learning, and Instinct: 100 Years of the Baldwin Effect. Special Issue of Evolutionary Computation on the Baldwin Effect 4(3) (1996)
Turney, P.: The Baldwin Effect: A Bibliography (1996), http://ai.iit.nrc.ca/baldwin/bibliography.html
Whitley, D., Gordon, S., Mathias, K.: Lamarckian Evolution, The Baldwin Effect and Function Optimization. In: Parallel Problem Solving from Nature (PPSN III), pp. 6–15. Springer, Heidelberg (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Spalanzani, A. (2000). Lamarckian vs Darwinian Evolution for the Adaptation to Acoustical Environment Change. In: Fonlupt, C., Hao, JK., Lutton, E., Schoenauer, M., Ronald, E. (eds) Artificial Evolution. AE 1999. Lecture Notes in Computer Science, vol 1829. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10721187_10
Download citation
DOI: https://doi.org/10.1007/10721187_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67846-5
Online ISBN: 978-3-540-44908-9
eBook Packages: Springer Book Archive