Abstract
This paper presents some results of our research regarding the speech processing systems based on Neural Networks (NN). The technology we are developing uses Evolutionary Algorithms for NN supervised training. Our current work is focused on Speech Synthesis and we are using a Genetic Algorithm to train and optimize the structure of a hyper-sphere type Neural Network classifier. These Neural Networks are employed at different stages of the Speech Synthesis process: recognition of syllables and stress in the high level synthesizer, text to phonemes translation, and control parameters generation for the low level synthesizer. Our research is included in a pilot project for the development of a bilingual (English and Romanian) engine for text to speech / automatic speech recognition and other applications like spoken e-mail, help assistant, etc.
Chapter PDF
Similar content being viewed by others
References
David Beasley, David R. Bull, Ralph R. Martin, An Overview of Genetic Algorithms, Part 2, Research Topics, Univerity Computing, 1993, 15(4) 170–181
G. E. Box and G. M. Jenkins, Time Series Analysis: Forecasting and Control, Holden Day, 1970.
[Dediu 1996]A. H. Dediu, D. Mihaila, Soft Computing Genetic Tool, Proceedings of First European Congress on Intelligent Techniques and oft Computing EUFIT’96, Aachen 2-5 September 1996, Vol. 2,pp. 415–418.
Dediu Adrian Horia, Agapie Alexandru, Varachiu Nicolae, Soft Computing Genetic Tool V3.0-Applications, 6-th Fuzzy Days in Dortmund-Conference on Computational Intelligence; 1999
T. Dutoit, V. Pagel, N. Pierret, F. Bataille, O. Van der Vrecken, The MBROLA project: Towards a Set of High Quality Speech Synthesizers Free of Use for Non Commercial Purposes Proc. ICSLP 96, Fourth International Conference on Spoken Language Processing, vol.3, p. 1393–1396, Philadelphia, 1996
D. E. Goldberg. Genetic Algorithms in search, optimization and machine learning. Addison-Wesley, 1989
M. Gori and F. Scarselli, Are Multilayer Perceptrons Adequate for Pattern Recognition and Verification?, IEEE Transactions on Patern Analysis and Machine Intelligence, November 1998, Volume 20,Number 11, pp. 1121–1132.
Richard P. Lippman, An Introduction to Computing with Neural Nets, IEEE ASSP MAGAZINE APRIL 1987.
Z. Michalewicz. Genetic Algorithms + Data Structures = Evolution Programs. Springer Verlag, 1992
Trandafir Moisa, Dan Ontanu, Learning Romanian Language Using Speech Synthesis, Advanced Research in Computers and Communications in Education, New Human Abilities for the Networked Society, Edited by Geoff Cumming, Tashio Okamoto, Louis Gomez, Proceedings of ICCE’99, 7th International Conference on Computers in Education, Chiba, Japan, pp. 808–815, IOS Press, Volume 55, 1999
Trandafir Moisa, Dan Ontanu, A Spoken E-mail System, 12th International Conference on Control Systems and Computer Science-CSCS12, May 26-29, 1999, Bucharest, Romania.
Trandafir MOISA, Adrian Horia DEDIU, Dan ONTANU, Conversational System Based on Evolutionary Agents, CEC 2000, International Conference on Evolutionary Computation USA 2000
Onţanu, D.-M. “Learning by Evolution. A New Class of General Classifier Neural Networks and Their Training Algorithm”, Advances in Modelling & Analysis, AMSE Press, Vol. 26,nr. 2/1993, pp. 27–30
Dan Ontanu, Voice Synthesis, referate for the PhD. thesis “Neural Models for Specch Recognition and Synthesis”, under the direction of prof. dr. Trandafir Moisa, author, “Politehnica” University, Bucharest, July 1998
Reilly, Cooper, Elbaum, ”A Neural Model for Category Learning”, Biological Cybernetics, 45, p. 35–41, 1982
Patrick Henry Winston, ”Artificial Intelligence” third ed., Addison-Wesley, June 1992
[Weigend 1994]A. S. Weigend, N. A. Gershenfeld (Eds.), Time Series Prediction: Forecasting the Future and Understanding the Past, Addison Wesley, 1994.
X. Yao: Evolving artificial neural networks, Proceedings of IEEE 87(9), pp. 1423–1447,September 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moisa, T., Ontanu, D., Dediu, A.H. (2001). Speech Synthesis Using Neural Networks Trained by an Evolutionary Algorithm. In: Alexandrov, V.N., Dongarra, J.J., Juliano, B.A., Renner, R.S., Tan, C.J.K. (eds) Computational Science - ICCS 2001. ICCS 2001. Lecture Notes in Computer Science, vol 2074. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45718-6_46
Download citation
DOI: https://doi.org/10.1007/3-540-45718-6_46
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42233-4
Online ISBN: 978-3-540-45718-3
eBook Packages: Springer Book Archive