Application of Temporal Neural Networks to Source Localisation

  • Brigitte Colnet
  • Stéphane Durand
Conference paper


In this paper, we present several neural networks approaches to deal with the problem of source localisation in signal processing. To locate a far field source, we have to retrieve the propagation delays between sensors. They are the only relevant temporal information we can handle on the signal.

As we have to process temporal data, we study different time representations in neural networks. First, time may be represented explicitly and externally with multilayer perceptrons. Then, we use a time-delay neural network that appears to be more suitable to represent explicitly the temporal nature of the signal. Last, we study recurrent neural networks that represent time in their internal organisation.


Hide Layer Input Layer Recurrent Neural Network Hide Unit Acoustic Event 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    F. Alexandre, F. Guyot, J P. Haton, and Y. Burnod. The cortical column: a new processing unit for multilayered networks. Neural networks, 4: 15–25, 1991.CrossRefGoogle Scholar
  2. [2]
    B. Ans. Modèle neuromimétique du stockage et du rappel de séquences temporelles. Académie des Sciences Paris, 3: 7–12, 1990.Google Scholar
  3. [3]
    W.S. Burdic. Underwater acoustic system analysis. Prentice-Hall signal processing series, Englewood Cliffs, New-Jersey, 1984.Google Scholar
  4. [4]
    B. Colnet and J.P. Haton. Far field array processing with neural networks. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pages 281–284, Adelaid, Australia, April 1994.Google Scholar
  5. [5]
    B. Colnet and J.C. Di Martino. Bearing estimation with time-delay neural networks. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Detroit, Michigan, May 1995.Google Scholar
  6. [6]
    S. Durand and F. Alexandre. A neural network based on sequence learning: Application to spoken digits recognition. In 7th international conference on Neural Networks and Their Applications, pages 290–298, Marseille, 1994.Google Scholar
  7. [7]
    S. Durand and F. Alexandre. Spatio-Temporal Mask Learning: Application to Speech Recognition. In International Conference on Artificial Neural Networks and Genetic Algorithms, Alès, April 1995.Google Scholar
  8. [8]
    J.L. Elman. Finding structure in time. Cognitive Science, 14: 179–211, 1990.CrossRefGoogle Scholar
  9. [9]
    M I. Jordan. Attractor dynamics and parallelism in a connectionist sequential machine. In Hillsdale, editor, Proceedings of the Eighth Annual Conference of the Cognitive Science Society. Erlbaum, 1986.Google Scholar
  10. 10]
    E.I. Knudsen, S. du Lac, and S.D. Esterly. Computational maps in the brain. Annual Review of Neuroscience, 10: 41–65, 1987.CrossRefGoogle Scholar
  11. [11]
    R.P. Lippmann. An introduction to computing with neural nets. IEEE Acoustics Speech and Signal Processing Society, 4 (2): 4–22, April 1987.Google Scholar
  12. [12]
    V.I. Nenov and M.G. Dyer. Perceptually grounded language learning: Part1-a neural network architecture for robust sequence association. Connection Science, 5 (2): 115–138, 1993.CrossRefGoogle Scholar
  13. [13]
    D.E. Rumelhart and J.L. McClelland. Parallel distributed processing: explorations in the microstructure of cognition, volume 1. MIT press, 1986.Google Scholar
  14. [14]
    N. Suga. Cortical computational maps for auditory imaging. Neural Networks, 3: 3–21, 1990.CrossRefGoogle Scholar
  15. [15]
    A. Waibel, T. Hanazawa, K. Shikano, and K.J Lang. Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37 (3): 328–339, March 1989.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Brigitte Colnet
    • 1
  • Stéphane Durand
    • 1
  1. 1.CRIN-CNRS INRIA LorraineVandœuvre-lès-NancyFrance

Personalised recommendations