A Novel Speech Enhancement Method Using Fourier Series Decomposition and Spectral Subtraction for Robust Speaker Identification

  • Ali I. Siam
  • Heba A. El-khobbyEmail author
  • Mustafa M. Abd Elnaby
  • Hatem S. Abdelkader
  • Fathi E. Abd El-Samie


This paper presents a novel speech enhancement approach by combining Fourier series expansion and spectral subtraction. This approach is implemented in speaker identification systems where degraded speech could result in high false speaker identifications. A Fourier series is estimated for the noisy speech signals, and then spectral subtraction is used to reduce the amount of noise in order to enhance quality of the speech signals before the speaker identification process. Experimental results presented to compare between the proposed approach and the traditional methods demonstrate the ability of the proposed approach to both enhance speech quality and improve speaker recognition rates.


Speech enhancement Speaker identification Voice authentication Fourier series Spectral subtraction 



  1. 1.
    Mavaddaty, S., Ahadi, S. M., & Seyedin, S. (2016). A novel speech enhancement method by learnable sparse and low-rank decomposition and domain adaptation. Speech Communication, 76, 42–60.CrossRefGoogle Scholar
  2. 2.
    Kamath, S., & Loizou, P. (2002). A multi-band spectral subtraction method for enhancing speech corrupted by colored noise. In IEEE international conference on acoustics, speech and signal processing, p. 4164.Google Scholar
  3. 3.
    El-Samie, F. E. A. (2011). Information security for automatic speaker identification. New York: Springer.CrossRefGoogle Scholar
  4. 4.
    Scalart, P., & Filho, J. (1996). Speech enhancement based on a priori signal to noise estimation. In IEEE international conference on acoustics, speech and signal processing, pp. 629–632.Google Scholar
  5. 5.
    Lu, Y., & Loizou, P. (2008). A geometric approach to spectral subtraction. Speech Communication, 50, 453–466.CrossRefGoogle Scholar
  6. 6.
    El-Fattah, M. A. A., Dessouky, M. I., Diab, S. M., & El-Samie, F. E. A. (2008). Speech enhancement using an adaptive wiener filtering approach. Progress in Electromagnetics Research, 4, 167–184.CrossRefGoogle Scholar
  7. 7.
    Osgood, B. (2013). Lecture notes for EE 261: The Fourier transform and its applications. Stanford University.‏Google Scholar
  8. 8.
    Reynolds, D., & Rose, R. (1995). Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, 3, 72–83.CrossRefGoogle Scholar
  9. 9.
    Kurzekar, P., Deshmukh, R., Waghmare, V., & Shrishrimal, P. (2014). A comparative study of feature extraction techniques for speech recognition system. IJIRSET, 3, 18006–18016.CrossRefGoogle Scholar
  10. 10.
    Linde, Y., Buzo, A., & Gray, R. M. (1980). An algorithm for vector quantizer design. IEEE Transactions on Communications, 28, 84–96.CrossRefGoogle Scholar
  11. 11.
    ITU-T Test Signals for Telecommunication Systems.
  12. 12.
    Kondo, K. (2012). “Subjective quality measurement of speech”, signals and communication technology (pp. 7–20). Berlin, Heidelberg: Springer. Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Ali I. Siam
    • 1
  • Heba A. El-khobby
    • 2
    Email author
  • Mustafa M. Abd Elnaby
    • 2
  • Hatem S. Abdelkader
    • 3
  • Fathi E. Abd El-Samie
    • 4
  1. 1.Department of Smart Network Systems Technology, Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikhEgypt
  2. 2.Department of Electronics and Electrical Communications Engineering, Faculty of EngineeringTanta UniversityTantaEgypt
  3. 3.Department of Information Systems, Faculty of Computers and InformationMenoufia UniversityMenoufiaEgypt
  4. 4.Department of Electronics and Electrical Communications, Faculty of Electronic EngineeringMenoufia UniversityMenouf 32952Egypt

Personalised recommendations