Advertisement

Improvements on Common Vector Approach Using k-Clustering Method

  • Seohoon Jin
  • MyungWoo Nam
  • Sang-Tae Han
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4303)

Abstract

In this paper, an advanced common vector approach (CVA) method for isolated word recognition is presented. The proposed method eliminates drawback of conventional CVA method, which is impossibility of being applied to a large number of training voices case, by dividing the training voices into a few small groups where those voices belong to a class of one of the spoken words. The results from using MFCC, LPC, LSP, Cepstrum, and auditory model shows that the proposed method solves the drawback of conventional CVA method. It got better recognition rate of 1.39% without significant changes of amounts of computation.

Keywords

Recognition Rate Reference Vector Training Vector Average Recognition Rate Voice Signal 
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.
    Bilginer, M., et al.: A novel approach to isolated word recognition, Speech and Audio Processing. IEEE Trans. 7, 620–628 (1999)Google Scholar
  2. 2.
    Hakan, C., Mitch, W.: Discriminative common vectors for face recognition. IEEE Trans. Pattern analysis and machine intelligence 27(1) (January 2005)Google Scholar
  3. 3.
    Gulmezoglu, M.B., Dzhafarov, V., Barkana, A.: The common vector approach and its relation to the principal component analysis. IEEE Trans. Speech and Audio Processing 9, 655–662 (2001)CrossRefGoogle Scholar
  4. 4.
    Gulmezoglu, M.B., Dzhafarov, V., Barkana, A.: Comparison of common vector approach and other subspace methods in case of sufficient data. In: Proc. 8th conference on Signal Processing and Applications, Belek, Turkey, pp. 13–18 (2000)Google Scholar
  5. 5.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley Interscience, Chichester (2001)MATHGoogle Scholar
  6. 6.
    Cho, C.H.: Modified k-means algorithm. The Journal of Acoustical Society of Korea 19(7), 23–27 (2000)Google Scholar
  7. 7.
    Wallace, G.K.: The JPEG still picture compression standard, Consumer Electron. IEEE Trans 38, 18–34 (1992)Google Scholar
  8. 8.
    Lay, D.C.: Linear algebra and its applications. Addison-Wesley, Reading (2000)MATHGoogle Scholar
  9. 9.
    Deller, J.R., Proakis, J.G., Hansen, J.H.L.: Discrete-time processing of speech signals. Macmillan Publishing Company, Basingstoke (1993)Google Scholar
  10. 10.
    Nam, M.W., Park, K.H., Jeong, S.G., Rho, S.Y.: Fast algorithm for recognition of Korean isolated word. The Journal of Acoustical Society of Korea 20(1), 50–55 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Seohoon Jin
    • 1
  • MyungWoo Nam
    • 2
  • Sang-Tae Han
    • 3
  1. 1.Department of Cross Sell Marketing, Hyundai CapitalSeoulKorea
  2. 2.Department of Digital Elecronics DesignHyejeon CollegeChoongnamKorea
  3. 3.Department of Informational StatisticsHoseo University29-1, AsanKorea

Personalised recommendations