KL: A neural model for capturing structure in speech

  • P. Frasconi
  • M. Gori
  • M. Maggini
  • G. Soda
Short Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 549)


In this paper we propose a neural model conceived for problems of word recognition and understanding of small protocol-driven sentences. The model is based on an unified approach to integrate priori knowledge and learning by example. The priori knowledge, injected into the network connections, can be of different levels, while learning is mainly conceived as a refinement process, and is responsible of dealing with uncertainty. We describe a small prototype for problems of isolated word recognition.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    De Michelis P., Fissore L., Laface P., Micca G., and Piccolo E., “On the Use of Neural Networks for Speaker Independent Isolated Word Recognition”, Proc. of IEEE-ICASSP89, Glasgow — Scotland, 1989.Google Scholar
  2. [2]
    Frasconi P., Gori M., and Soda G., “Recurrent Networks for Continuous Speech Recognition”, Computational Intelligence 90, Milan (Italy), September 1990, Elsevier.Google Scholar
  3. [3]
    Frasconi P., Gori M., Soda G. “Local Feedback Multi Layered Networks”, Neural Computation (to appear).Google Scholar
  4. [4]
    Frasconi P., Gori M., Maggini M., and Soda G., “An Unified Approach for Integrating Explicit Knowledge and Learning by Example in Recurrent Networks”, Proc. of IEEE-IJCNN91, Seattle (Washington), 1991. (to appear).Google Scholar
  5. [5]
    Gori M., Bengio Y. and De Mori R., BPS: “A Learning Algorithm for Capturing the Dynamical Nature of Speech”. Proceedings of the IEEE-IJCNN89. Washington June 18–22.Google Scholar
  6. [6]
    Gori M., Tesi A., “On the Problem of Local Minima in Back-Propagation”, IEEE Trans. PAMI (to appear).Google Scholar
  7. [7]
    Judd S, “On the Complexity of Loading Shallow Neural Networks”, Journal of Complexity, 4, 1988.Google Scholar
  8. [8]
    Kammerer B.K. and Kupper W.A., “Design of Hierarchical Perceptron Structures and their Application to the Task of Isolated Word Recognition”, Proceedings of the IEEE-IJCNN89. Washington June 18–22.Google Scholar
  9. [9]
    Pealing S.M., Moore R.K., and Tomlinson M.J., “The Multi-Layer Perceptron as a Tool for Speech Pattern Processing Research”, Proc. of the 10th Autumn Conference on Speech and Hearing, 1986.Google Scholar
  10. [10]
    Pearlmutter B. A., “Learning State Space Trajectories in Recurrent Neural Networks”, Neural Computation, vol 1, no. 2, Summer 1989.Google Scholar
  11. [11]
    Waibel A., Hanazawa T., Hinton G., Shikano K., Lang K., “Phoneme Recognition Using Time-Delay Neural Networks”, IEEE Transactions on ASSP, vol. 37, no. 3, March 1989.Google Scholar
  12. [12]
    Watrous R.L. “Speech Recognition Using Connectionist Networks”, Ph.D. Thesis, University of Pennsylvania, Philadelphia, PA 19104, November 1988.Google Scholar
  13. [13]
    Williams R.J., Zipser D., “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks”. Neural Computation, vo. 1, no. 1, pp. 270–280, 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • P. Frasconi
    • 1
  • M. Gori
    • 1
  • M. Maggini
    • 1
  • G. Soda
    • 1
  1. 1.Dipartimento di Sistemi e InformaticaVia S. Marta 3Firenze

Personalised recommendations