Employing FPGA Accelerator in Real-Time Speaker Identification Systems

  • Omran Al-Shamma
  • Mohammed A. FadhelEmail author
  • Haitham S. Hasan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 922)


In the most recent years, numerous approaches have been accomplished in the discipline of human voice recognition for building speaker identification systems. Frequency and time domain techniques are widely used in extracting human voice features. This paper presents the most robust and most popular Mel-frequency cepstral coefficient (MFCC) technique to parameterize voices and to be used later in the voiced/unvoiced different feature extraction process methods. In addition, the direct classical techniques for human voice feature extraction purposes are used. For the purpose of the processing time consumption and to speed up the system performance for use in real-time applications, a field programming gate array (FPGA) is utilized. Its type is Altera DE2 Cyclone II.


Speech recognition MFCC Human voice identification FPGA Real-time classification 


  1. 1.
    Gaikwad SK (2010) A review on speech recognition technique. Int J Comput Appl (0975–8887) 10(3)Google Scholar
  2. 2.
    Bachu RG, et al (2008) Separation of voiced and unvoiced using zero crossing rate and energy of the speech signal. In: American Society for Engineering Education (ASEE) zone conference proceedingsGoogle Scholar
  3. 3.
    Kaur G, Singh D, Kaur G (2015) A survey on speech recognition algorithms. Int J Emerg Res Manage Technol 4(5):289–298Google Scholar
  4. 4.
    Shrawankar U, Thakare V (2010) Techniques for feature extraction in speech recognition system: a comparative study. Int J Comput Appl Eng Technol Sci (IJCAETS) 2(1):412–418Google Scholar
  5. 5.
    Poonkuzhali C, Karthiprakash R, Valarmathy S, Kalamani M (2013) An approach to feature selection algorithm based on ant colony optimization for automatic speech recognition. Int J Adv Res Electr Electron Instrum Eng 11(2) (2013)Google Scholar
  6. 6.
    Majeed S, Husain H, Abdulsamad S, Idbeaa T (2015) Mel Frequency Cepstral Coefficients (MFCC) feature extraction enhancement in the application of speech recognition: a comparison study. J Theor Appl Inf Technol 79(1):38–56Google Scholar
  7. 7.
    Rabiner LR, Juang BBH (1993) Fundamentals of speech recognition. Prentice Hall, ‎Upper Saddle RiverGoogle Scholar
  8. 8.
    Huang X, Acero A, Hon H-W (2001) Spoken language processing, vol 15. Prentice Hall, ‎Upper Saddle RiverGoogle Scholar
  9. 9.
    Von Békésy G, Wever EG (1960) Experiments in hearing, vol 8. McGraw-Hill, New YorkGoogle Scholar
  10. 10.
    Quatieri TF (2002) Discrete-time speech signal processing. Pearson Education, LondonGoogle Scholar
  11. 11.
    Xiong X (2009) Robust speech features and acoustic models for speech recognition. PhD. Thesis, Nanyang Technological University, SingaporeGoogle Scholar
  12. 12.
    Rabiner LR, Schafer RW (2010) Theory and applications of digital speech processing. Pearson, LondonGoogle Scholar
  13. 13.
    Ephraim Y, Rahim M (1999) On second-order statistics and linear estimation of Cepstral coefficients. IEEE Trans Speech Audio Process 7:162–176CrossRefGoogle Scholar
  14. 14.
    Singh P, Rani P (2014) An approach to extract features using MFCC. IOSR J Eng 4(8):21–25CrossRefGoogle Scholar
  15. 15.
    Churiwala S, Hyderabad I (2017) Designing with Xilinx® FPGAs. Springer International Publishing, ChamCrossRefGoogle Scholar
  16. 16.
    Bailey DG (2011) Design for embedded image processing on FPGAs. Wiley, New YorkCrossRefGoogle Scholar
  17. 17.
    EhKan P, Allen T, QuigleySF (2011) FPGA implementation for GMM-based speaker identification. Int J Reconfig Comput 3Google Scholar
  18. 18.
    Chu PP (2012) Embedded SoPC design with NIOS II processor and Verilog examples. Wiley, New YorkCrossRefGoogle Scholar
  19. 19.
    Khan ARM, Thakare AP, Gulhane SM (2010) FPGA-based design of controller for sound fetching from codec using Altera DE2 Board. Int J Sci Eng Res 1(2)Google Scholar
  20. 20.
    Altera DSP (2003, July) Builder–reference manual. Altera CorporationGoogle Scholar
  21. 21.
    Mathworks Homepage. Last Accessed 1 Sep 2018
  22. 22.
    Nurmi J et al (eds) (2015) GALILEO positioning technology. Springer, BerlinGoogle Scholar
  23. 23.
    Tlelo-Cuautle E, de la Fraga LG, Rangel-Magdaleno J (2016) Engineering applications of FPGAs. Springer, BerlinCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Omran Al-Shamma
    • 1
  • Mohammed A. Fadhel
    • 1
    Email author
  • Haitham S. Hasan
    • 1
  1. 1.University of Information Technology and CommunicationsBaghdadIraq

Personalised recommendations