Identifying Sound of RPW In Situ from External Sources

  • Betty Martin
  • P. E. Shankaranarayanan
  • Vimala Juliet
  • A. Gopal
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 324)


Over the last decade, speech recognition has been used in the field of security system, gender identification for automatic speech recognition, pattern recognition, biometrics, voice finger, dragon naturally speaking, etc. In the recent past, lots of research works are being carried out in these fields. The proposed research work also deals with one such interesting system, wherein the characteristics of the sound generated by red palm weevil (RPW) for recognition of their presence in the palm in a nondestructive way is done. For this work, a text-independent identification system makes use of feature extraction and feature matching technique. The sound of RPW recorded is compared against external sources for easy detection. Out of the several techniques available for feature extraction and comparison, mel-frequency cepstral coding (MFCC) technique has been utilized for feature extraction and the comparison is being carried out using vector quantization (VQ).


Speech recognition Red palm weevil Mel-frequency cepstral coding Vector quantization RB signal 


  1. 1.
    B. Martin, V. Juliet, A novel approach to identify red palm weevil on palms, in The Proceedings of 2nd International Conference on Chemical, Material and Metallurgical Engineering ICCMME (2012)Google Scholar
  2. 2.
    B. Martin, V. Juliet, Distinguishing features of RPW from RB present in palms by signal processing, in The Proceedings of International Conference on Trends in Industrial measurements and Automation—TIMA2011 (2011), pp. 668–671Google Scholar
  3. 3.
    B. Martin, V. Juliet, Extraction of features from acoustic activity of RPW using MFCC, in The Proceedings of International Conference on Recent Advances in Space Tech Services & Climate Change—RSTS&CC (2010), pp. 194–197Google Scholar
  4. 4.
    Q. Li, Y. Huang, Robust speaker identification using an auditory based feature, in ICASSP (2002), pp. 4514–4517Google Scholar
  5. 5.
    S. Singh, E.G. Rajan, Vector quantization approach for speaker recognition using MFCC and inverted MFCC. Int. J. Comput. Sci. Secur. 1(3) (2011)Google Scholar
  6. 6.
    S. Chin et al., A speaker verification system. ELEC 499A Final Report (2002), pp. 1–34Google Scholar
  7. 7.
    L. Tan, M. Karnjanadecha, Modified mel frequency cepstral coefficient, in Proceedings of the Information Engineering Post Graduate Workshop (2003), pp. 127–130Google Scholar
  8. 8.
    T. El Bachir, Design of an automatic speaker recognition system based on adapted MFCC and GMM methods for Arabic speech. Int. J. Comput. Sci. Netw. Secur. 10(10), 45–50 (2010)Google Scholar
  9. 9.
    K.K. Paliwal, Chapter 7 Book on MFCC quantization in distributed speech recognition (Springer, Berlin), pp. 295–350Google Scholar
  10. 10.
    V. Tiwari, MFCC and its application in speaker recognition. Int. J. Emerg. Technol. 1(1), 19–22 (2010)Google Scholar
  11. 11.
    W. Yutai, et al., Speaker recognition based on dynamic MFCC parameters, in International Conference on Image Analysis and Signal Processing (2009), pp. 406–409Google Scholar
  12. 12.
    P. Tellez, J. Savage, Isolated sentences recognition using vector quantization and neural network, in SPECOM’2006 (2006)Google Scholar
  13. 13.
    H.B. Kekre, V. Kulkarni, Speaker identification by using vector quantization. Int. J. Eng. Sci. Technol. 2(5), 1325–1331 (2010)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • Betty Martin
    • 1
  • P. E. Shankaranarayanan
    • 1
  • Vimala Juliet
    • 2
  • A. Gopal
    • 3
  1. 1.Sathyabama UniversityChennaiIndia
  2. 2.SRM UniversityChennaiIndia
  3. 3.CEERIChennaiIndia

Personalised recommendations