Abstract
In this paper we present a phoneme recognition system based on predictive neural networks. Both feed-forward and recurrent neural networks are used for the prediction of observation vectors of speech frames. Preliminary experiments are conducted to study the discriminative quality of the prediction error as distortion measure and other similarity measures based on the Gaussian and Rayleigh distributions. The average prediction error of the neural networks is interpreted as a new feature generated by the neural net through nonlinear feature transformation. The proposed system is evaluated on a continuous speech phoneme recognition task. The recognition results that we obtain with the proposed neural network based system are compared with results obtained by a continuous density HMM system.
Preview
Unable to display preview. Download preview PDF.
References
N. Morgan, H. Boulard. “Neural Networks for Statistical Recognition of Continuous Speech”, Proc. of the IEEE, pp. 742–770, vol. 83, no. 5, May 1995.
J. Tebelskis, A. Waigel, B. Petek. O. Schmidbauer. “Continuous speech recognition using Linked Predictive Neural Networks”. Proc. ICASSP, pp. 61–64, Toronto, 1991.
K. Na, J. Ryu, D. Chang, S.Chae, S. Ann. “Recurrent neural prediction models for speech recognition”. Proc. EUROSPEECH, pp. 2213–2216, Madrid, September 1995.
F. Freitag, E. Monte. “Acoustic-Phonetic Decoding based on Elman Predictive Neural Networks”. Proc. ICSLP, pp. 522–525, Philadelphia 1996.
M. Paping, H. Marti, M. Renfer, “Predictive connectionist speech recognition with a new discriminant learning algorithm”, Proc. EUROSPEECH, pp. 2193–2196, Madrid, September 1995.
S. Furui. “Speaker-Independent Isolated Word Recognition using Dynamic Features of the Speech Spectrum. IEEE ASSP-34(1) pp 52–59 February 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Freitag, F., Monte, E. (1997). Phoneme recognition by means of predictive neural networks. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032573
Download citation
DOI: https://doi.org/10.1007/BFb0032573
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive