A speech recognition system that integrates neural nets and HMM

  • E. Monte
  • J. B. Mariño
Part of the Lecture Notes in Computer Science book series (LNCS, volume 540)


In this paper we present a speech recognition system based on neural networks and on Hidden Markov Models. This system makes use of the discriminating properties of the multilayer perceptron, the properties of the fonotropical maps of Kohonen for clustering data and the properties for dealing with sequentiallity of the Hidden Markov Models (HMM). We also present preliminary results.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. /1/.
    C.H. Lee, "Speaker-Independent Continuous Speech Recognition Using Continuous Density Hidden Markov Models". Nato Advanced Study Institute. Cetraro 90. Italia.Google Scholar
  2. /2/.
    H. Bourlard y C.Wellekens. "Links between Markov Models and Multilayer Perceptrons". Informe Interno de Philips Research Laboratory. Sept.88 BruselasGoogle Scholar
  3. /3/.
    N.Morgan y H. Boulard. "Continuous Speech Recognition using Multilayer Perceptrons with Hidden markov Models". ICASSP90. Albuquerque.Google Scholar
  4. /4/.
    F.Fallside, H. Lucke, T.Marsland. "Continuous speech recognition for the TIMIT database using neural networks". ICASSP 90Google Scholar
  5. /5/.
    A.Waibel, T.Hanazawa, G.Hinton,K.Shikano, K.Lang. "Phoneme Recognition using Time Delay Neural Networks". IEEE, Trans. ASSP. vol 37. No3. Marzo 1989.Google Scholar
  6. /6/.
    J. Elman. "Finding structure in time". CRL Technical Report 8801. Abril 88. Center for Research in Language. University of California.Google Scholar
  7. /7/.
    M. Jordan. "Serial Order: A Parallel Distributed Processing Approach". ICS Report 8604. Mayo 86. Institute for Cognitive Science. University of California.Google Scholar
  8. /8/.
    T.Kohonen, "The Neural Phonetic Typewriter". IEEE Computer, Vol. 21,No3, Marzo 88.Google Scholar
  9. /9/.
    T.Kohonen, K. Torkola, M. Shazakai, J. Kangas, O.Venta. "Phonetic Typewriter for Finnish and Japanese". pp 607 ICASSP 88.Google Scholar
  10. /10/.
    E.Monte, J.B. Mariño, E.LLeida. "Alisado de los Modelos De Markov mediante Redes Fonotrópicas. Alicación al Reconocimiento del Habla." SEPLN-91.Google Scholar
  11. /11/.
    E. Monte, J.B.Mariño. "Modelos de Markov y cuantificación vectorial por medio de redes de Kohonen". URSI-91. Caceres.Google Scholar
  12. /12/.
    . M.Franzini,K.F.Lee,A.Weibel. "Connectionist viterbi training: a new hybrid method for continuous speech recognition" ICASSP-90Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • E. Monte
    • 1
  • J. B. Mariño
    • 1
  1. 1.Dpt. de Teoría de la Señal y ComunicacionesETSITB.UPC. ApartadoBarcelona

Personalised recommendations