Artificial Neural Networks for Analysis and Recognition of Primate Vocal Communication

  • Axel Zimmermann

Abstract

A number of simulated neurons form an artificial neural network. They are connected together in a way similar to biological neural systems. It is the high interconnection rate and the build-in parallelism of these networks that allow completely different processing capabilities in comparison to conventional computer systems. The performance of current pattern recognition systems is far below of humans’ abilities. Artificial neural networks offer the potential of providing new approaches to such problems.

Keywords

Artificial Neural Network Hide Markov Model Speech Recognition Speech Signal Automatic Speech Recognition 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bartkova, K., and Jouvet, D., 1991, Modelization of allophones in a speech recognition system, Proc. XIIth International Conference of Phonetic Science. Vol. 4: 474–477.Google Scholar
  2. Cole, R. A., Fanty,M., Gopalakrishnan, M., and Janssen, D. T., 1991, Speaker-independent name retrieval from spelling using a database of 50,000 names, IEEE Proc ICASSP: 14–17.Google Scholar
  3. Deng, L., and Erler, K., 1992, Structural design of a hidden Markov-model-based recognizer using multivalued phonetic features: Comparison with segmental speech units, J. Acoust. Soc. Am., 92: 3058–3067.PubMedCrossRefGoogle Scholar
  4. Hampshire, J. B., and Waibel, A. H., 1990, A novel objective function for improved phoneme recognition using time-delay neural networks, IEEE Trans. Neural Networks. Vol. 1, 2: 443–446.CrossRefGoogle Scholar
  5. Hebb, D., 1949, “The Organization of Behavior”, John Wiley, New York.Google Scholar
  6. Iso, K., and Watanabe, T., 1990, Speaker-independent word recognition using a neural prediction model, IEEE Proc. ICASS. Vol. 4: 443–446.Google Scholar
  7. Kohonen, T., 1984, “Series in Information Sciences: Vol. 8. Self-Organization and Associative Memory”, Springer-Verlag, Berlin-Heidelberg-New York-Tokyo.Google Scholar
  8. Kohonen, T., 1988, The neural phonetic typewriter, IEEE Computer, 3: 11–22.CrossRefGoogle Scholar
  9. Kosko, B. (ed.), 1992, “Neural Networks for Signal Processing”, Prentice-Hall, New Jersey.Google Scholar
  10. Lang, K. J., Waibel, A., and Hinton, G., 1990, A time-delay neural network for isolated word recognition, Neural Networks, 3: 23–29.CrossRefGoogle Scholar
  11. Lenning, M., 1990, Putting speech recognition to work in the telephone network, IEEE Computer, 8: 35–41. McCulloch, W., and Pitts, W., 1943, A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biophysics, 5: 115–121.Google Scholar
  12. Mead, C., 1989, “Analog VLSI and Neural Systems”, Addison-Wesley.Google Scholar
  13. O’Malley, M.H., 1990, Text-to-speech conversion technology, IEEE Computer, 8:17–23. O’Shaunessy, D., 1987, “Speech Communication: Human and Machine”, Addison-Wesley.Google Scholar
  14. Rabiner, L. R., Wilpon, J. G., and Soong, F. K., 1988, High-performance connected-digit recognition using hidden Markov models, IEEE Proc. ICASSP: 119–125.Google Scholar
  15. Ritter, H., Martinetz, T., and Schulten, K., 1990, “Neuronale Netze”, Addison-Wesley, Bonn. Rosenblatt, F., 1958, The perceptron: a probabilistic model for information storage and organization in the brain, Psychol. Review, 65: 386–408.Google Scholar
  16. Rojas, R., 1993, “Theorie der neuronalen Netze”, Springer, Berlin, Heidelberg, New York.Google Scholar
  17. Rummelhart, D., and McClelland, J., 1986, “Parallel Distributed Processing”, MIT Press, Cambridge-Massachusetts.Google Scholar
  18. Strathmeyer, C. R., 1990, Voice in computing: an overview of available technologies, IEEE Computer, 8: 10–15.CrossRefGoogle Scholar
  19. Unnikrishnan, K. P., Hopfield, J. J., and Tank, D. W., 1991, Connected-digit speaker-dependent speech recognition using a neural network with time-delayed connections, IEEE Trans. Sig. Proc. Vol. 39, 3: 698–713.CrossRefGoogle Scholar
  20. Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., and Lang, K., 1987, Phonem recognition using time-delay neural networks, IEEE Trans. ASSP. Vol. 3: 393–404.Google Scholar
  21. Waibel, A., Sawai, H., and Shikano, K., 1989, Consonant and phonem recognition by modular construction of large phonemic time-delay neural networks, Proc. ICASSP: 405–408.Google Scholar
  22. Zimmermann, A., 1992, Mikroelektronische Schaltung zum Aufbau selbstorganisierender Karten aus digitalen Neuronen, Offenlegungsschrift, Deutsches Patentamt DE 4227707 Al, G 06 F 15 /18.Google Scholar
  23. Zimmermann, E., and Lerch, C., 1993, The complex acoustic design of an advertisement call in male mouse lemurs (Microcebus murinus) and sources of its variation, Ethology 93: 211–224.CrossRefGoogle Scholar
  24. Zwicker, E., 1982, “Psychoakustik”, Springer, Berlin,Heidelberg,New York,Tokyo.CrossRefGoogle Scholar
  25. Zwicker, E., and Fastl, H., 1990, “Psychoacoustics - Facts and Models”, Springer, Berlin, Heidelberg.Google Scholar

Copyright information

© Springer Science+Business Media New York 1995

Authors and Affiliations

  • Axel Zimmermann
    • 1
  1. 1.Institut für InformatikUniversität StuttgartStuttgartGermany

Personalised recommendations