Abstract
In this paper we present a simple connectionist model for the adaptive sensorymotor loop involved in perceiving and producing speech. At the heart of the production part lies an articulatory model which approximates the human vocal tract through polygons and splines. Output of this model is the envelope of the acoustic filter function, realized by this vocal tract, which is comparable to the spectrum of real speech segments. The goal of this research was to find a learning method to train a multi-layer neural network to produce the correct set of twelve articulatory parameters when given the spectrum of recorded real speech (stationary vowels). The method introduced in this paper explicitly makes use of a neural network categorization component. Through so-called soft competitive learning it learns to gradually compress the responses to more and more unitized categorical patterns. After a precategorization phase, during which presented real speech patterns are classified, the model starts to randomly produce output signals. A goodness-of-fit measure, which can be computed easily, is taken as the criterion whether the self-produced signal is close enough to any of the known categories, and as the learning rate to adapt the weights between the categorization layer and the output units.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
Cohen M.A., Grossberg S., Stork D.G.: Speech Perception and Production by a Self-organizing Neural Network, in Lee Y.C.(ed.), Evolution, Learning and Cognition, World Scientific Publishing Co., London, p. 217–231, 1989.
Grossberg S.: Adaptive pattern classification and universal recoding, I: Parallel development and coding of neural feature detectors, Biological Cybernetics 21, 145–159, 1976.
Grossberg S.: Studies of mind and brain, Reidel Press, Boston, 1982.
McClelland J.L., Rumelhart D.E.: An Interactive Activation Model of Context Effects in Letter Perception: Part 1. An Account of Basic Findings, Psychological Review 88, 375–407, 1981.
Miller T.W., Sutton R.S., Werbos P.J.(eds.): Neural Networks for Control, MIT Press, Cambridge, 1991.
Rumelhart D.E., Zipser D.E.: Feature Discovery by Competitive Learning, Cognitive Science 9(1) 75–112, 1985.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer Science+Business Media New York
About this chapter
Cite this chapter
Dorffner, G., Schönauer, T. (1993). Unsupervised Learning of Simple Speech Production Based on Soft Competitive Learning. In: Eeckman, F.H., Bower, J.M. (eds) Computation and Neural Systems. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-3254-5_55
Download citation
DOI: https://doi.org/10.1007/978-1-4615-3254-5_55
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6431-3
Online ISBN: 978-1-4615-3254-5
eBook Packages: Springer Book Archive