Systolic Architectures for Connected Speech Recognition

  • Patrice Frison
  • Patrice Quinton
Conference paper
Part of the NATO ASI Series book series (volume 16)

Abstract

Systolic algorithm concept is introduced and three speech recognition algorithms are presented together with a systolic version. The first algorithm is based on the dynamic time warping algorithm which is applied directly on acoustic feature patterns. The second algorithm is the probabilistic matching algorithm which requires that the input sentence be preprocessed by a phonetic analyzer. The third algorithm is the connected word recognition algorithm that find the best matching word sequence. Finally, the architecture of a speech recognition machine using a VLSI chip, called API89, as the basic processor is presented.

Keywords

Convolution Univer 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    L.J. Siegel, “Highly Parallel Architectures and Algorithms for Speech Analysis,” 1984 Int. Conf. Acoustic, Speech, Signal Processing, San Diego, March 1984, pp. 85A.1.1–25A.1.4.Google Scholar
  2. [2]
    H.T. Kung, “Why Systolic Architectures?,” Computer, Vol. 15, No 1, Jan 1982, pp. 37–46.CrossRefGoogle Scholar
  3. [3]
    N. Weste, D.J, Burr, and B.D. Ackland, “Dynamic Time Warp Pattern Matching Using an Integrated Multiprocessing Array,” IEEE Trans. Comp., Vol. C-32, Aug. 1983, pp. 731–744.CrossRefGoogle Scholar
  4. [4]
    M.A. Yoder and L.J. Siegel, “Dynamic Time Warping Algorithms for SIMD Machines and VLSI Processor Arrays,” 1982 Int. Conf. Acoustic, Speech, Signal Processing, Paris, May 1982, pp. 1274–1277.Google Scholar
  5. [5]
    J.A. Feldman, S.L. Gaverick, F.M. Rhodes, and J.R. Mann, “A Wafer Scale Integration Systolic Processor for Connected Word Recognition,” 1984 Int. Conf. Acoustic, Speech, Signal Processing, San Diego, March 1984, pp. 25B.4.1– 25B.4.4.Google Scholar
  6. [6]
    J.P Banatre, P. Frison, and P. Quinton, “A Network for the Detection of Words in Continuous Speech,” Proceedings of the VLSI 81 Int. Conference, Edimburg, Aug. 1981.Google Scholar
  7. [7]
    J.P. Banatre, P. Frison, and P. Quinton, “A Systolic Algorithm for Speech Recognition,” 1982 Int. Conf. Acoustic, Speech, Signal Processing, Paris, May 1982, pp. 1243–1245.Google Scholar
  8. [8]
    J.P. Banatre, P. Frison, and P. Quinton, “A Network for the Detection of Words in Continuous Speech,” Acta Informatica 18, pp. 431–448.Google Scholar
  9. [9]
    P. Frison, “Un Processeur Integre pour la Reconnaissance de la Parole,” INRIA Research Report No. 215, July 1983.Google Scholar
  10. [10]
    L. R. Bahl, and F. Jelinek, “Decoding for Channels with Insertions, Deletions, and Substitutions with Applications to Speech Recognition,” IEEE Trans. Informat. Theory, Vol IT-21, No 4, pp 404–411, 1976Google Scholar
  11. [11]
    C. Mead, L. Conway, Introduction to VLSI Systems, Addison Wesley Publishing Company Inc., 1980.Google Scholar
  12. [12]
    P.Quinton, “The Systematic Design of Systolic Arrays” MCNC Technical Report, TR84-11, May 84.Google Scholar
  13. [13]
    R. Bellman, S. Dreyfus, Applied Dynamic Programming, Princeton University Press, New-Jersey, 1962.MATHGoogle Scholar
  14. [14]
    H. Sakoe and S, Chiba, “Dynamic Programming Algorithm Optimization For Spoken Word Recognition,” IEEE Trans. Acoust, Speech, Signal Processing, Vol. ASSP-26, No. 1, Feb. 1978, pp. 43–49.CrossRefGoogle Scholar
  15. [15]
    G. Mercier, A. Nouhen, P. Quinton, and J. Siroux, “The Keal Speech Understanding System,” In: Spoken Language Generation and Understanding, J.C. Simon (Ed), Proc. NATO ASI, Bonas, 1980.Google Scholar
  16. [16]
    J. Bridle, M. Brown, and R. Chamberlain, “An algorithm for Connected Word Recognition,” 1982 Int. Conf. Acoustic, Speech, Signal Processing, Paris, May 1982, pp. 899–902.Google Scholar
  17. [17]
    C. Myers, and L.R. Rabiner, “A Level Building Dynamic Time Warping Algorithm for Connected Word Recognition,” IEEE Trans, on Acoust., Speech, Signal Processing, Vol ASSP-29, No. 3, April 1083, pp. 351–363.Google Scholar
  18. [18]
    H. Sakoe, “Two-Level DP-Matching — A Dynamic Programming-Based Pattern Matching Algorithm for Connected Word Recognition,” IEEE Trans. Acoust. Speech. Signal Processing. Vol ASSP-28, No. 4, Aug. 1980, pp. 588–595.CrossRefGoogle Scholar
  19. [19]
    L. Buisson, G. Mercier, J.Y. Gresser, M. Querre, and R. Vives, “Phonetic Decoding for Automatic Recognition of Words”, Speech Communication Seminar, Stockholm, Aug. 1974Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1985

Authors and Affiliations

  • Patrice Frison
    • 1
  • Patrice Quinton
    • 1
  1. 1.IRISARennes-CedexFrance

Personalised recommendations