Hetero-Associative Memories for Voice Signal and Image Processing

  • Roberto A. Vázquez
  • Humberto Sossa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5197)

Abstract

An associative memory AM is a type of neural network commonly used for recalling output patterns from input patterns that might be altered by noise. Most of these models have several constraints that limit their applicability in complex problems. Recently, in [13] a new AM based on some aspects of human brain was introduced, however the authors only test its accuracy using image patterns. In this paper we show that this model is also robust with other type of patterns such as voice signal patterns. The AM is trained with associations composed by voice signals and their corresponding images. Once trained, when a voice signal is used to stimulate the AM we expect the memory recall the image associated to the voice signal. In order to test the accuracy of the proposal, a benchmark of sounds and images was used.

Keywords

Associative memories voice signal processing image processing 

References

  1. 1.
    Steinbuch, K.: Die Lernmatrix. Kybernetik 1, 26–45 (1961)MATHGoogle Scholar
  2. 2.
    Anderson, J.A.: A simple neural network generating an interactive memory. Math. Biosci. 14, 197–220 (1972)CrossRefMATHGoogle Scholar
  3. 3.
    Kohonen, T.: Correlation matrix memories. IEEE Trans. on Comp. 21, 353–359 (1972)CrossRefMATHGoogle Scholar
  4. 4.
    Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Sussner, P.: Generalizing operations of binary auto-associative morphological memories using fuzzy set theory. J. Math. Imaging Vis. 19, 81–93 (2003)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Ritter, G.X., et al.: Reconstruction of patterns from noisy inputs using morphological associative memories. J. Math. Imaging Vis. 19, 95–111 (2003)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Sossa, H., Barron, R., Vazquez, R.A.: Transforming Fundamental set of Patterns to a Canonical Form to Improve Pattern Recall. In: Lemaître, C., Reyes, C.A., González, J.A. (eds.) IBERAMIA 2004. LNCS (LNAI), vol. 3315, pp. 687–696. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Ritter, G.X., Sussner, P., Diaz de Leon, J.L.: Morphological associative memories. IEEE Trans Neural Networks 9, 281–293 (1998)CrossRefGoogle Scholar
  9. 9.
    Sussner, P., Valle, M.: Gray-Scale Morphological Associative Memories. IEEE Trans. on Neural Netw. 17, 559–570 (2006)CrossRefGoogle Scholar
  10. 10.
    James, W.: Principles of Psychology. Holt, New York (1890)CrossRefGoogle Scholar
  11. 11.
    Vazquez, R.A., Sossa, H., Garro, B.A.: 3D Object recognition based on low frequencies response and random feature selections. In: Gelbukh, A., Kuri Morales, Á.F. (eds.) MICAI 2007. LNCS (LNAI), vol. 4827, pp. 694–704. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Vazquez, R.A., Sossa, H., Garro, B.A.: Low frequency responses and random feature selection applied to face recognition. In: Kamel, M., Campilho, A. (eds.) ICIAR 2007. LNCS, vol. 4633, pp. 818–830. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Vazquez, R.A., Sossa, H.: A new associative memory with dynamical synapses. Neural Processing Letters (submitted, 2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Roberto A. Vázquez
    • 1
  • Humberto Sossa
    • 1
  1. 1.Centro de Investigación en Computación – IPN, Av. Juan de Dios Batíz, esquina con Miguel Othón de Mendizábal, Ciudad de MéxicoMéxico

Personalised recommendations