Abstract
The use of Time-Delay Neural Networks (TDNN's) in Continuous Speech Recognition has not been as relevant as it was expected due to the computational costs implied by Time-Delay orders, as it was taken for granted that the bigger the orders, the better the representation of the dynamic essence of Speech. This paper focuses on the true differential nature of this representation, and proposes to see TDNN's as devices working on differential relations among delayed versions of Speech Spectra, using Lattice Predictors as processing delay lines, which de-correlate the information which is presented to the computing nodes. This results in optimally compact structures (minimum number of delays), and better convergence rates. Convergence experiments show that reductions in the global computational costs as low as 1∶5 may be achieved using structures based on this method as compared with traditional TDNN's.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
J. T. Connor, R. D. Martin, and L. E. Atlas, “Recurrent Neural Networks and Robust Time Series Prediction”, IEEE Trans. on Neural Networks, Vol. 5, No. 2, March 1994, pp. 240–253.
Dugast, C. Devillers, L. and Aubert, X., “Combining TDNN and HMM in a Hybrid System for Improved Continuous-Speech Recognition”, IEEE Trans. on Signal Processing, Vol. 2, No. 1, January 1994, pp. 217–223.
S. Haykin, Adaptive Filters, Prentice-Hall, Englewood Cliffs, NJ, 1991.
D. P. Morgan and C. L. Scofield, Neural Networks and Speech Processing, Kluwer Academic Publishers, Boston, MA, 1991.
V. Rodellar, P. Gómez, M. Pérez, V. Nieto, R. Romera and J. Muruzábal, “Dimensionality and Dynamic Temporal Structure of a Time-Delay Neural Network for Speech Processing”, Proc. of EUSIPCO'94, Edinburgh, September 13–16, 1994, pp. 816–819.
V. Rodellar, V. Nieto, P. Gómez, D. Martinez and M. Pérez, “A Neural Network for Phonetically Decoding the Speech Trace”, Proc. of the Intern. Conf. on Spoken Language Proc. '94, Yokohama, Japan, 1994, pp. 1575–1578.
D. W. Ruck, S. K. Rogers, M. Kabrisky, P. S. Maybeck and M. E. Oxley, “Comparative Analysis of Backpropagation and the Extended Kaiman Filter for Training Multilayer Perceptrons”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 6, June 1992, pp. 686–691.
A. Waibel, T. Hanazawa, G. Hinton, K. Shikano and K. J. Lang, “Phoneme Recognition Using Time-Delay Neural Networks”, IEEE Trans. on ASSP, Vol. 37, No. 3, March 1989, pp. 328–339.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gómez, P., Rodellar, V., Nieto, V., Hombrados, M.A. (1995). A lattice-based Time-Delay Neural Network for speech processing. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_274
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_274
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive