Abstract
In this paper, some results of the classification of spanish phonemes by means of Kohonen Self-Organizing Maps (SOM) are presented. These results show that SOM may be very useful in the previous steps of a continous speech recognizer, as well as a valuable aid in the signal phonetic segmentation process. This intermediate classification provides a new representation of the signal such that the “phonetic” gap between inputs and outputs of the recognizer is drastically reduced, so simplifying the task of the recognizer.
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
Kohonen, T.: The “Neural” Phonetic Typewriter. IEEE Computer, March 1988. 11–22
Kohonen, T.: The Self-Organizing Map Proceedings of the IEEE. Vol. 78, N.9. September (1990)
Kohonen, T., Hynnimen, J., Kangas, J., Laaksonen, J.: The Self-Organizing Map Program Package version 3.1. SOM programming team of the university of technology. Laboratory of computer and information science. Finland. (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gardón, A.P., Vázquez, C.R., Illarramendi, A.A. (1999). Spanish Phoneme Classification by Means of a Hierarchy of Kohonen Self-Organizing Maps. In: Matousek, V., Mautner, P., Ocelíková, J., Sojka, P. (eds) Text, Speech and Dialogue. TSD 1999. Lecture Notes in Computer Science(), vol 1692. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48239-3_33
Download citation
DOI: https://doi.org/10.1007/3-540-48239-3_33
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66494-9
Online ISBN: 978-3-540-48239-0
eBook Packages: Springer Book Archive