Abstract
Most ANN techniques do not address the problem of the varying duration of speech utterances, and of the timing of speech events within utterances. This is because the networks employed generally require fixed dimensional input. An example of fixed dimensional input is given in [1], where the recognition of whole words is achieved by capturing the word and linearly adjusting its duration to fit the ANN’s input window, as illustrated in Fig. 1.
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
Woodland P. C. & Smyth S. G.: ‘A Neural Network Speech Recogniser for Directory Access Applications’, Proc Voice Systems Worldwide, p196 (1990).
Rabiner L. R.: ‘A Tutorial of Hidden Markov Models and Selected Applications in Speech Recognition’, Proc IEEE, 77(2), p257 (1989).
Morgan N. & Bourlard H.: ‘Continuous Speech Recognition using Multilayer Perceptron with Hidden Markov Models’, Proc ICASSP-90, p413 (1990).
Rumelhart D. E., Hinton G. E. & Williams R. J.: ‘Learning internal representations by error propagation’, in ‘Parallel Distributed Processing: Explorations in the Microstructure of Cognition’, eds Rumelhart & McClelland, MIT Press Cambridge, Ma (1986).
Bourlard H. & Wellekens C. J.: ‘Links between Markov Models and Multilayer Perceptrons’, IEEE Trans Pattern Analysis and Machine Intelligence 12, Part 12, p1167 (1990).
Rabiner L. R., Wilpon J. G. & Juang B. H.: ‘A segmental k-means training procedure for connected word recognition’, AT&T Tech J, 65(3), p21 (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 British Telecommunications plc
About this chapter
Cite this chapter
Smyth, S.G. (1992). Segmental Sub-Word Unit Classification Using a Multilayer Perceptron. In: Linggard, R., Myers, D.J., Nightingale, C. (eds) Neural Networks for Vision, Speech and Natural Language. BT Telecommunications Series, vol 1. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-2360-0_13
Download citation
DOI: https://doi.org/10.1007/978-94-011-2360-0_13
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-5041-8
Online ISBN: 978-94-011-2360-0
eBook Packages: Springer Book Archive