Abstract
In this paper we describe a more robust vector quantization model for speech based on spatiotemporal clustering. The principle of self-organization in time is employed to create traveling waves, which are gradually attenuated over time and space to diffuse temporal information and create localized temporal neighborhoods for classification of speech. We also define performance functions for quantification of this method, based on the time varying property of Voronoi cells. This method is better than conventional static vector quantizers built on the same data set and similar training conditions.
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
Euliano N. R, Principe J. C. A spatio-temporal memory based on SOMs with activity diffusion, Workshop on Self-Organizing Maps, Helsinki, Finland, 1999, 253-266.
Euliano N. R. Temporal Self-Organization for Neural Networks, PhD Dissertation, Graduate School of University of Florida, Gainesville, USA, 1998.
Euliano N. R, Principe J. C. Spatiotemporal self-organizing feature maps, in Proc IJCNN 1996.
Martinetz T. M, Berkovich S. G, Schulten K. J. Neural Gas Network for Vector Quantization and Application to Time Series Prediction, IEEE Transaction on Neural Networks, July 1993, 4: 558-569.
Turing A. The Chemical basis of Morphogenesis, in Phil Transactions of the Royal Society of London, Ser.B, 1952; 237: 37-72.
Murray J. D. Mathematical Biology, Springer-Verlag, New York, 1989.
Baretto G. A, Araujo A. F. Time in Self-Organizing Maps: An overview of models.
Rabiner L, Juang B. H. Fundamentals of Speech Recognition, Prentice Hall Signal Processing Series, 1993.
ICRA Noise Signals ver.0.3 CDROM, International Collegium of Rehabilitative Audiology, Feb 1997.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag London Limited
About this paper
Cite this paper
Garani, S., Principe, J.C. (2001). Dynamic Vector Quantization Of Speech. In: Advances in Self-Organising Maps. Springer, London. https://doi.org/10.1007/978-1-4471-0715-6_31
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0715-6_31
Publisher Name: Springer, London
Print ISBN: 978-1-85233-511-3
Online ISBN: 978-1-4471-0715-6
eBook Packages: Springer Book Archive