Abstract
The paper reviews a number of methods for continuous speech recognition, concentrating mostly on work at Cambridge University. The methods reviewed are a ‘sound’ and phoneme recogniser using duration sensitive nets; the modified Kanerva model for phoneme recognition; a recurrent net for phoneme recognition; a Classification and Regressive Tree (CART) for phoneme recognition; together with methods for lexical access including the NET-gram, the modified Kanerva model, and the ‘Compositional Representation’ approach
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
Breiman, L., Friedman, J.H., Olshen, R.A. & Stone, C.J.: Classification and Regression Trees, Wadsworth & Brooks/Cole, 1984.
Bridle, J.: Alpha-Nets: A recurrent neural network architecture with HMM interpretation, Speech Communication, April, 1990.
Chan, L.W & Fallside, F..: An adaptive training algorithm for back propagation networks, Computer Speech & Language, 3, 3/4, Sept/Dec 1987, 205–218.
Chong, M.W. & Fallside, F.: Classification and regression tree neural networks for automatic speech recognition, Proc. INNC90, Paris, 1, 187–190.
Chow, Y.L., Dunham, M.O., Kimball, O.A., Krasner, M.A., Kubela, G.F., Makhoul, J., Roucos, S., & Schwartz, R.M.: BYBLOS: The BBN continuous speech recognition system, Proc. ICASSP 87, Dallas 1987, 89–92.
Fallside, F., Lucke, H., Marsland, T.P., O’Shea, P.J., Owen, M. St.J., Prager, R.W., Robinson, A.J. & Russell, N.H.: Continuous speech recognition for the TIMIT database using neural networks, Proc. ICASSP 90, Albuquerque, 1990, pp.445–448.
Fisher, W.M., Zue, V., Bernstein, J., Pallett, D.: An acoustic-phonetic database, Proc. Acoustic Soc. Amer., May 1987.
Harrison, T.D. & Fallside, F.: A connectionist model for phoneme recognition in continuous speech, Proc. ICASSP 89, Glasgow, 1989, 417–420.
Kanerva, P.: Self-propagating search: a unified theory, Ph.D thesis, Stanford University, Centre for Study of Language and Information, 1984.
Lee, K-F.: Automatic Speech Recognition: The Development of the SPHINX System, Kluwer (Boston), 1989.
Lee, K-F & Hon, H-W.: Speaker independent phoneme recognition using HMMs, IEE Trans. ASSP, 37, (11), 1989, 1641–1648.
Lucke, H. & Fallside.: Application of the Compositional Representation to lexical access using neural networks, Proc. Intl. Conf. on Spoken Language Processing, Kobe, November 1990, paper 31.13.
Nakamura, M. & Shikano, K.: A study of English word category prediction based on neural networks, Proc. ICASSP 89, Glasgow 1989, 731–734.
Prager, R.W. & Fallside, F.: The modified Kanerva model for automatic speech recognition, Computer Speech & Language, 3, 1, 1989, 61–81.
Prager, R.W., Clarke, T.J.W. & Fallside, F.: The modified Kanerva model: results for real time word recognition, IEE Intl. Conf. on Artificial Neural Networks, London, 1989, 105–109.
Price, P.J., Fisher, W., Bernstein, J., Pallett, D.: The DARPA 1000-word resource management database for continuous speech recognition, Proc. ICASSP 88, New York, 1988, 651–654.
Robinson, A.J. & Fallside, F.: A dynamic connectionist model for phoneme recognition, Proc. n’Euro ‘88, ENST, Paris 1988.
Robinson, A.J. & Fallside, F.: Phoneme recognition for the TIMIT database using recurrent error propagation networks, Technical Report CUED/F/INFENG/TR42, March 1990, Cambridge University Engineering Department, (submitted for publication).
Robinson, A.J., Holdsworth, J., Patterson, R. & Fallside, F.: A comparison of preprocessors for the Cambridge recurrent error propagation network speech recognition system, Proc. Intl. Conf. on Spoken Language Processing, Kobe, November 1990, paper 23.17.
Robinson, A.J. & Fallside, F.: Further results from the DARPA resource management database with the Cambridge Recurrent Error Propagation Speech Recognition System, submitted to ICASSP 90.
Young, S.J.: Competitive training in Hidden Markov Models, Proc. ICASSP 90, Albuquerque, 1990, 681–684.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fallside, F. (1992). Neural Networks for Continuous Speech Recognition. In: Laface, P., De Mori, R. (eds) Speech Recognition and Understanding. NATO ASI Series, vol 75. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76626-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-76626-8_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76628-2
Online ISBN: 978-3-642-76626-8
eBook Packages: Springer Book Archive