Abstract
A comparison among neural net models (Multilayer Perceptron, Time Delay, and Recurrent neural networks) is proposed. The aim is to evaluate, from a practical point of view, their performance on a problem of classification of phonemes. The efficacy and the limitation of each model will be discussed in the light of their dependence on free parameters like the number of hidden nodes, learning rate and initial weight values.
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
Bishop C. M., Neural Network for Pattern Recognition, Clarendon Press, 1995.
Rummelhart D.E., McClelland J.L., Parallel Distributed Processing: Explorations, in the Microstructure of Cognition, MIT Press, 1986.
Waibel A., Hanazawa T., Hinton G.E., Shikano K., Lang K.J., Phoneme Recognition using Time Delay Neural Networks, Technical Report TR-1–0006, ATR Interpreting Telephony Research Laboratories, 1987.
Waibel A., Sawai H., Shikano K., Modularity and Scaling in Large Phonemic Neural Networks, Technical Report TR 10034, ATR Interpreting Telephony Research Laboratories, July, 1988.
Waibel A., Hanazawa T., Hinton G.E., Shikano K., Lang K.J., Phoneme Recognition Using Time Delay Neural Networks, IEEE Trans. Acoust. Speech Signal Process, 1989, 37 (3), 328–339.
Elman J. L., Finding Structure in Time, Cognitive Science vol. 14, pag.179–221. 1990.
Jordan M. I., Attractor Dynamics and Parallelism in a Connectionist Sequential Machine, Proc. of 8th Ann. Conf. of the Cognitive Science Society, pp. 532–546, Hillsdale NJ, Erlbaum, 1986.
Jordan M. I., Serial Order: a Parallel Distributed Processing Approach, Technical Report Nr. 8604, Institute for Cognitive Science, University of California, San Diego, La Jolla, California, 1986a.
Stuttgart Neural Network Simulator (SNNSv4.1), 1990–1995. Institute for parallel and distributed high performance systems, University of Stuttgart.
Hermansky H., Perceptual Linear Predictive (PLP) Analysis of Speech, Jour. Acoust. Soc. Am., 1990, 87(4), 1738–1752.
Hermansky H., Morgan N., RASTA Processing of Speech, IEEE Trans. On Speech and Audio Processing, 1994, 2(4), 578–589.
Renals S., Rohwer S., Phoneme Classification Experiments Using Radial Basis Functions, Proc. of Int. Joint Conf. on Neural Networks, Vol I, pp.461–67, 1989.
Hecht-Nielsen R., Counterpropagation Networks, Proc. Int. Conf. on Neural Networks, Vol. II, New York, pp. 19–32,1987.
Hecht-Nielsen R., Neurocomputing, Addison-Wesley, Reading, MA, 1989.
Powell M. J. D., Algorithms for Approximation, Oxford, 1987.
Broomhead D. S., Lowe D., Complex Systems 2, 1988.
Kolmogorov A. N., On the Representation of Continuous Functions of Many Variables by Superposition of Continuous Functions of One Variable and Addition, Dokl. Akad. Nauk, USSR, Vol 114, 1957, pp.953–56.
Haykin S., Neural Networks - A Comprensive foundation, IEEE Press, 1994.
Hertz J., Krogh A., Palmer R.G., Introduction to the Theory of Neural Computation, Lecture Notes Volume I, Santa Fe Institute Studies in Sciences of Complexity, 1991.
Williams R. J., Peng J., An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories, Neural Computation 2, 490–501, 1990.
Williams R. J., Zipser D., A Learning Algorithm for Continually Running Fully Recurrent Neural Networks, Neural Comp., 1, 270–280, 1989.
Almeida L. B., A Learning Rule for Asynchronous Perceptrons with Feedback in a Combinatorial Environment, Proc. IEEE First Int. Conf. Neural Networks, II, 609–618, 1987.
Pineda F. J., Generalization of Back-Propagation to Recurrent Neural Networks, The American Physical Society, Vol. 59, Number 19, 1987.
Hopfield J. J., Neurons with Graded Response Have Collective Computational Properties Like Those Two-State Neurons, Proc. of the National Academy of Sciences, USA, Vol. 81, 1984, pp. 3088–92.
Esposito A., Ezin E. C., Phoneme Classification using a RASTA-PLP preprocessing algorithm and a Time Delay Neural Network: Performance Studies, Proc. of WIRN98, M. Marinaro, R. Tagliaferri (eds), pp. 207–217, Springer-Verlag Publisher, 1998.
Ström N., Sparse Connection and Pruning in Large Dynamic Artificial Neural Networks, Proc. of EUROSPEECH, vol. 5, 2807–2810, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag London Limited
About this paper
Cite this paper
Esposito, A., Aversano, G., Quek, F. (2002). Optimal Parameters in Neural Network Models for Speech Phoneme Characterization. In: Tagliaferri, R., Marinaro, M. (eds) Neural Nets WIRN Vietri-01. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0219-9_18
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0219-9_18
Publisher Name: Springer, London
Print ISBN: 978-1-85233-505-2
Online ISBN: 978-1-4471-0219-9
eBook Packages: Springer Book Archive