Skip to main content

Measurement of finite-precision effects in handwriting- and speech-recognition algorithms

  • Part VIII: Implementations
  • Conference paper
  • First Online:
Artificial Neural Networks — ICANN'97 (ICANN 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1327))

Included in the following conference series:

  • 101 Accesses

Abstract

This paper reports experiments measuring the effects of finite precision arithmetic in the range of 4 to 16 bits on three particular pattern-recognition algorithms: an optical character recognizer [1], a pen-based character recognizer [2], and a speech recognizer [3]. The measurements shows that large portions of these algorithms can be implemented with 8-bit arithmetic (e.g. using Intel's MMXTM instruction set) while incurring only a negligible loss in recognition accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Yann LeCun, Bernhard Boser, John S. Denker, Donnie Henderson, Richard E. Howard, Wayne Hubbard, and Lawrence D. Jackel. Handwritten digit recognition with a back-propagation network. In David S. Touretzky, editor, Neural Information Processing Systems, volume 2, pages 396–404. Morgan Kaufmann Publishers, San Mateo, CA, 1990.

    Google Scholar 

  2. Markus Schenkel, Haim Weissman, Isabelle Guyon, Craig Nohl, and Donnie Henderson. Recognition-based segmentation of on-line hand-printed words. In S. J. Hanson and J. D. Cowan C. L. Giles, editors, Neural Information Processing Systems, volume 5, pages 723–730. Morgan Kaufmann Publishers, San Mateo, CA, 1993.

    Google Scholar 

  3. Enrico L. Bocchieri. A study of the beam-search algorithm for large vocabulary continuous speech recognition and methods for improved efficiency. In Proc. EuroSpeech, volume 3, pages 1521–1524, September 1993.

    Google Scholar 

  4. Linley Gwennap. Intel's MMX speeds multimedia. Microprocessor Report, pages 1–10, March 1996.

    Google Scholar 

  5. Linley Gwennap. Digital, MIPS add multimedia extensions. Microprocessor Report, pages 24–28, November 1996.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Wulfram Gerstner Alain Germond Martin Hasler Jean-Daniel Nicoud

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Säckinger, E. (1997). Measurement of finite-precision effects in handwriting- and speech-recognition algorithms. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020318

Download citation

  • DOI: https://doi.org/10.1007/BFb0020318

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63631-1

  • Online ISBN: 978-3-540-69620-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics