Advertisement

An approach to isolated word recognition using multilayer perceptrons

  • A. Cañas
  • J. Ortega
  • F. J. Fernández
  • A. Prieto
  • F. J. Pelayo
Applications
Part of the Lecture Notes in Computer Science book series (LNCS, volume 540)

Abstract

Neural networks offer the potential of providing massive parallelism, adaptation, and new algorithm approaches to speech recognition. In this communication, we show a new approach to face the problem of speaker-independent isolated word recognition with the Multilayer Perceptron (MLP), trained with Backpropagation algorithm. This approach lies in a preprocessing similar to that used for Kohonen Networks, thus in the context of unsupervised learning, which allows to overcome the temporal alignment problem of word samples and to reduce the number of neurons in the MLPs. As a preliminary result, the performances of MLPs for recognizing sequences of vowels in isolated words, after learning with samples of isolated vowels, are presented.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Lippmann, R.P.:"Review of Neural Networks for Speech Recognition". Neural Computation 1, pp.1–38. 1989.Google Scholar
  2. [2]
    Ye, H.;Wang, S.;Robert, F.:"A PCMN Neural Network for Isolated Word Recognition". Speech Communication, 9, North-Holland, pp.141–153. 1990.Google Scholar
  3. [3]
    Gibson, G.; Cowan, C.F.N.:"On the Decision Regions of Multilayer Perceptrons". Proc.IEEE, Vol.78, No.10, pp.1590–1594. October, 1990.Google Scholar
  4. [4]
    Waibel, A.;Hanazawa, T.;Hinton, G.;Shikano, K.; Lang, K.J.:"Phoneme Recognition Using Time-Delay Neural Networks". IEEE Trans. on Acoust. and Sign.Proc., Vol.37, No.3, pp.328–339. March, 1989.Google Scholar
  5. [5]
    Puchol, C.;Casacuberta, F.:"Reconocimiento de Palabras aisladas mediante Redes Neuronales". Comunicaciones del IV Simposium Nacional de Reconocimiento de Formas y Análisis de Imágenes. Granada, Septiembre, 1990.Google Scholar
  6. [6]
    Kohonen, T.:"The Self-Organizing Map". Proc. IEEE, Vol.78, No.9, pp.1464–1480. September, 1990.Google Scholar
  7. [7]
    Kong, S-G.; Kosko, B:"Differential Competitive learnig fo Centroid Estimation and Phoneme Recognition". IEEE Trans. on Neural Nets., Vol.2, No.1, pp.118–124. January, 1991.Google Scholar
  8. [8]
    Minsky, M.; Paper, S.:"Perceptrons". MIT Press, Cambridge, MA. 1969.Google Scholar
  9. [9]
    Widrow, B.;Lehr, M.:"30 Years of Adaptative Neural Networks: Perceptron, Madaline, and Backpropagation". Proc.IEEE, Vol.78, No.9, pp.1415–1442. September, 1990.Google Scholar
  10. [10]
    Bernasconi,J.:"Analysis and Comparison of Different Learning Algorithms for Patterns Association Problems". American Institute of Physics, 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • A. Cañas
    • 1
  • J. Ortega
    • 1
  • F. J. Fernández
    • 1
  • A. Prieto
    • 1
  • F. J. Pelayo
    • 1
  1. 1.Departamento de Electrónica y Tecnología de ComputadoresUniversidad de GranadaGranadaSpain

Personalised recommendations