Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Comparison of neural networks and conventional techniques for automatic recognition of a multilingual speech database

  • Applications
  • Conference paper
  • First Online:
Artificial Neural Networks (IWANN 1991)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 540))

Included in the following conference series:

Abstract

The paper presents an exhaustive test between the Multilayer Perceptron Fully Connected (MLPFC) trained with backpropagation using the feedback learning rule on one side and three well-established non-NN, standard Isolated Word Recognition (IWR) techniques on the other, using to this aim a multilingual speech database formed by a common vocabulary in three languages: German, Italian and Spanish. This comparative testing has been centered on speaker-independent conditions and two different training subsets have been used. An additional multi-speaker test has been performed on the Spanish vocabulary in order to compare the performances of the MLPFC and backpropagation with feedback learning algorithm with the non-NN methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. M.H. Kuhn, H. Tomaschewski, H. Ney. "Fast Non-linear Time Alignment for Isolated Word Recognition". Proceedings of the ICASSP, 1981 (pp. 736–740).

    Google Scholar 

  2. L. Rabiner, J. Wilpon. "Considerations in Applying Clustering Techniques to Speaker-Independent Word Recognition". J. Acoust. Soc. An. 66, 1979 (pp. 663–673).

    Google Scholar 

  3. D. O'Shanghnessy. Speech Communication. Addison-Wesley, 1987.

    Google Scholar 

  4. M. Cohen, S. Grossberg, D. Stork. "Recent Developments in a Neural Model of Real-Time Speech Analysis and Synthesis". Proceedings of the IEEE First International Conference on Neural Networks, Vol. IV, 1987 (pp. 443–454).

    Google Scholar 

  5. T. Kohonen, K. Makisara, T. Saramaki. "Phonotopic Maps: Insightful Representation of Phonological Features for Speech Recognition". Proceedings of the 7th International Conference on Pattern Recognition, 1984 (pp. 182–185).

    Google Scholar 

  6. T. Kohonen. "Learning Vector Quantization". Neural Networks Supplement: INNS Abstracts, 1, 303.

    Google Scholar 

  7. J.-H. Pao. Adaptive Pattern Recognition and Neural Networks. Addison-Wesley, 1989.

    Google Scholar 

  8. R. Momenan et al. "Characterization of Tissue from Ultrasound Images". IEEE Control Magazine, vol. 8, No. 3, 1988 (pp. 49–53).

    Google Scholar 

  9. L. Kaufman, P.J. Rousseeuw. Finding Groups in Data: An Introduction to Cluster Analysis. Wiley Interscience, 1990.

    Google Scholar 

  10. D. Maravall, J. Ríos, M. Pérez, A. Carpintero, J. Gómez-Calcerrada. Intermediate Report on the Test of the C-library Algorithms for the Multilingual Speech Database. ESPRIT II — Project 2059, PYGMALION. June 28, 1990.

    Google Scholar 

  11. Ibidem. Final Report on the Test of the C-library Algorithms for the Multilingual Speech Database. ESPRIT II — Project 2059, PYGMALION. December 15, 1990.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Alberto Prieto

Rights and permissions

Reprints and permissions

Copyright information

© 1991 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Maravall, D., Ríos, J., Pérez-Castellanos, M., Carpintero, A., Gómez-Calcerrada, J. (1991). Comparison of neural networks and conventional techniques for automatic recognition of a multilingual speech database. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035917

Download citation

  • DOI: https://doi.org/10.1007/BFb0035917

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-54537-8

  • Online ISBN: 978-3-540-38460-1

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics