Implementing a Hidden Markov Model Speech Recognition System in Programmable Logic

  • Stephen J. Melnikoff
  • Steven F. Quigley
  • Martin J. Russell
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2147)


Performing Viterbi decoding for continuous real-time speech recognition is a highly computationally-demanding task, but is one which can take good advantage of a parallel processing architecture. To this end, we describe a system which uses an FPGA for the decoding and a PC for pre- and post-processing, taking advantage of the properties of this kind of programmable logic device, specifically its ability to perform in parallel the large number of additions and comparisons required. We compare the performance of the FPGA decoder to a software equivalent, and discuss issues related to this implementation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Melnikoff, S.J., James-Roxby, P.B., Quigley, S.F. & Russell, M.J., “Reconfigurable computing for speech recognition: preliminary findings,” FPL 2000, LNCS #1896, pp. 495–504.Google Scholar
  2. 2.
    Rabiner, L.R., “A tutorial on Hidden Markov Models and selected applications in speech recognition,” Proceedings of the IEEE, 77, No. 2, 1989, pp. 257–286.CrossRefGoogle Scholar
  3. 3.
    Woodland, P.C., Odell, J.J., Valtchev, V. & Young, S.J. “Large vocabulary continuous speech recognition using HTK,” ICASSP’ 94, 2, pp. 125–128.Google Scholar
  4. 4.
    Young, S., “A review of large-vocabulary continuous-speech recognition,” IEEE Signal Processing Magazine, 13, No. 5, 1996, pp. 45–57.CrossRefGoogle Scholar
  5. 5.
  6. 6.
  7. 7.
  8. 8.
  9. 9.

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Stephen J. Melnikoff
    • 1
  • Steven F. Quigley
    • 1
  • Martin J. Russell
    • 1
  1. 1.School of Electronic and Electrical EngineeringUniversity of BirminghamEdgbastonUK

Personalised recommendations