Noisy Speech Recognition Using Kernel Fuzzy C Means

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 801)

Abstract

In the area of voice recognition, soft computing technique is a prominent method to identify and cluster speaker variability’s in the speech signal. But whenever the signal is convoluted by a noisy signal standard FCM method fails to give the good results. To overcome this, Kernel FCM (KFCM) is used in this paper. PCA helps in reducing the features of convoluted signal. The recognition results are compared with and without applying PCA using KFCM function and the same is presented for word recognition rate.

Keywords

Cepstral Coefficients (MFCC) Soft computing technique Additive noise Convolution noise Computation Complexity (CC) Principal Component Analysis (PCA) Kernel Fuzzy C Means (KFCM) 

Notes

Acknowledgment

The authors remain thankful for all the persons who have helped us in understanding and formulating the paper. We acknowledge Dr. S. K. Katti, for making us to understand the mathematical concepts behind the soft computing techniques.

References

  1. 1.
    Rabiner, L., Juang, B.H.: Fundamentals of Speech Recognition, vol. 103. Prentice Hall Englewood Cliffs, New Jersy (1996)MATHGoogle Scholar
  2. 2.
    Anusuya, M.A., Katti, S.K.: Front end analysis of speech signal processing: a review. Int. J. Speech Technol. 14, 99–145 (2011).  https://doi.org/10.1007/s10772-010-9088-7CrossRefGoogle Scholar
  3. 3.
    Linde, Y., Buzo, A., Gray, R.: An algorithm for vector quantizer design. IEEE Trans. Commun. 28, 84–95 (1980)CrossRefGoogle Scholar
  4. 4.
    Tran, D.-T.: Fuzzy approaches to speech and speaker recognition, thesis submitted to University of Canberra, May 2000Google Scholar
  5. 5.
    Bezdek, C.: A convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Trans. 0162-8828/80/0100-0001Google Scholar
  6. 6.
    Wang, X., Wang, Y., Wang, L.: Improving fuzzy c-means clustering based on feature-weight learning. Pattern Recogn. Lett. 25, 1123–1132 (2004).  https://doi.org/10.1016/j.patrec.2017.02.015CrossRefGoogle Scholar
  7. 7.
    Zhang, D.: Kernel-Based Associative Memories, Clustering Algorithms and their Applications, Nanjing University of Aeronautics and Astronautics (2004)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Sri Jayachamarajendra College of EngineeringMysoreIndia

Personalised recommendations