A Speaker Independent Isolated Word Recognition System for Turkish

  • Ö. B. Tüzün
  • E. Erzin
  • M. Demirekler
  • A. T. Memişoğlu
  • M. S. Uğur
  • A. E. Çetin
Conference paper
Part of the NATO ASI Series book series (volume 147)

Abstract

In this paper, a speaker independent isolated word recognition system based on hidden Markov models (HMM) having a vocabulary of 12 Turkish words is presented. Several LPC representations are tested as feature vectors and the obtained results are compared.

Keywords

Feature Vector Hide Markov Model Speech Recognition Speech Signal Recognition Accuracy 
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. [1]
    J. R. Deller, Jr., J. G. Proakis, J. H. L. Hansen, Discrete-Time Processing of Speech Signals. MacMillan Publishing Company, New York, 1993Google Scholar
  2. [2]
    L.R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” Proceedings of the IEEE, Vol. 77, No. 2, pp. 257–285, Feb. 1989CrossRefGoogle Scholar
  3. [3]
    K. K. Paliwal, “On the Use of Line Spectral Frequency Parameters for Speech Recognition,” Digital Signal Processing: A Review Journal, Vol. 2, No. 2, pp. 80–87, April 1992CrossRefGoogle Scholar
  4. [4]
    L. F. Lamel, L. R. Rabiner, A. E. Rosenberg, “An Improved Endpoint Detector for Isolated Word Recognition,” IEEE Trans, on ASSP, Vol. 29, No. 4, pp. 777–784, Aug. 1981CrossRefGoogle Scholar
  5. [5]
    Y. Linde, A. Buzo, R. M. Gray, “An Algorithm for Vector Quantizer Design” IEEE Trans. on Comm., Vol. 28, No. 1, pp. 84–95, Jan. 1980CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Ö. B. Tüzün
    • 2
  • E. Erzin
    • 1
  • M. Demirekler
    • 3
  • A. T. Memişoğlu
    • 3
  • M. S. Uğur
    • 2
  • A. E. Çetin
    • 1
  1. 1.Department of Electrical and Electronics EngineeringBilkent UniversityAnkaraTurkey
  2. 2.The Scientific and Technical Research Council of TurkeyAnkara Electronics Research and Development Institute, Digital Speech Processing Laboratory, METU Department of Electrical and Electronics EngineeringAnkaraTurkey
  3. 3.Department of Electrical and Electronics EngineeringMiddle East Technical UniversityAnkaraTurkey

Personalised recommendations