Spatio-temporal pattern recognition with neural networks: Application to speech

  • Jean Rouat
Part I: Coding and Learning in Biology
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1327)


The processing or the recognition of non stationary process with neural networks is a challenging and yet unsolved issue. The paper discuss the general pattern recognition framework using neural networks in relation with the understanding of the peripheral auditory system. We propose a short-time structure representation of speech for speech analysis and recognition. We give examples of neural networks architecture and applications that are designed to take into account the time structure of the process to be analysed.


Auditory Cortex Periodicity Code Speaker Verification Novelty Detector Speech Recogniser 
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.
    Alkon, D.L., Blackwell, K.T., Barbourg, G.S., Rigler, A.K. and Vogl, T.P.: Pattern-recognition by an artificial network derived from biologic neuronal systems. Biological Cybernetics, vol. 62 (1990) 363–376Google Scholar
  2. 2.
    Frisina, R. D. et al.: Differential encoding of rapid changes in sound amplitude by second-order auditory neurons. Exp. Brain Res., vol. 60 (1985) 417–422Google Scholar
  3. 3.
    Ho, T. V. and Rouat, J.: A Novelty Detector using a Network of Integrate and Fire Neurons. ICANN97.Google Scholar
  4. 4.
    Langner, G. and Schreiner, C.E.: Periodicity coding in the inferior colliculus of the cat. Neuronal mechanisms. Journal of Neurophysiology, vol.60, 6, (1988) 1799–1822Google Scholar
  5. 5.
    Patterson, R.D.: Auditory filter shapes derived with noise stimuli. Journal of the Acoustical Society of America, vol. 59, 3 (1976) 640–654Google Scholar
  6. 6.
    Rouat, J. and Garcia, M.: A prototype speech recogniser based on associative learning and nonlinear speech analysis. In Proc. of the Workshop on Computational Auditory Scene Analysis, International Joint Conference (IEEE-ACM) on Artificial Intelligence, (1995) 7–12. To be published in, Readings In Computational Auditory Scene Analysis, Edited by H. Okuno and D. Rosenthal, ErlbaumGoogle Scholar
  7. 7.
    Schreiner, C. E. and Urbas, J. V.: Representation of amplitude modulation in the auditory cortex of the cat. I. The anterior auditory field (AAF). Hearing Research, vol. 21 (1986) 227–241Google Scholar
  8. 8.
    Schreiner, C.E. and Langner, G.: Periodicity coding in the inferior colliculus of the cat. Topographical organization. Journal of Neurophysiology, vol. 60, 6 (1988) 1823–1840Google Scholar
  9. 9.
    Shannon, R. V et al.: Speech Recognition with Primarily Temporal Cues. Science, vol. 270 (1995) 303–304Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Jean Rouat
    • 1
    • 2
  1. 1.ERMETIS, Sciences AppliquéesUniversité du Québec á ChicoutimiQuébec
  2. 2.Neuro-Heuristique, I.P., Faculté de MédecineUniversité de LausanneLausanne

Personalised recommendations