Wavelet basis selection for enhanced speech parametrization in speaker verification

  • Authors:

  • Todor Ganchev;Mihalis Siafarikas;Iosif Mporas;Tsenka Stoyanova

  • Affiliations:

  • Department of Electronics, Technical University---Varna, Varna, Bulgaria 9010;Department of Electrical & Computer Engineering, University of Patras, Rion-Patras, Greece 26500;Dept. of ECE, University of Patras, Patras, Greece 26500 and Dept. of Mechanical Engineering, Technological Educational Institute of Patras, Patras, Greece 26334;Department of Electrical & Computer Engineering, University of Patras, Rion-Patras, Greece 26500

  • Venue:
  • International Journal of Speech Technology
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

We study the inherent properties of nine wavelet functions and subsequently evaluate their applicability as basis functions in a speech parametrization scheme that is advantageous for speaker verification. Particularly, the inherent properties of nine candidate basis functions are initially analysed and their advantages and disadvantages are discussed. Subsequently, all candidates are employed in a well-proven speech parametrization scheme, and the resulting speech features are computed. Finally, these speech features are evaluated in a common experimental set-up on the speaker verification task. The experimental results, obtained on two well-known speaker recognition databases, show that the Battle-Lemarié wavelet function is the most advantageous one, among all other functions evaluated here, since it leads to the most beneficial speech descriptors. When compared to the baseline Mel-frequency cepstral coefficients (MFCC), a relative reduction of the equal error rate by 4.2 % was observed on the 2001 NIST speaker recognition evaluation database, and by 2.3 % on the Polycost speaker recognition database.