An FPGA implementation of the local global graph-based voice biometric authentication scheme

  • Authors:
  • Raghudeep Kannavara;George Bebis;Nikolaos Bourbakis

  • Affiliations:
  • Wright State University, College of Engineering ATR Center, Dayton, OH;University of Nevada-Reno, CSE Dept., Reno, NV;Wright State University, College of Engineering ATR Center, Dayton, OH and AIIS Inc., Dayton, Ohio

  • Venue:
  • DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this work, we present a novel method for authentication based on voice biometrics. Local graphs of the preprocessed speech signal are first calculated by feature extraction and combined to form a Global graph that is stored in a database for the purpose of authentication. The distance between the Global graphs of the presented test speech signal and the stored reference speech signal is then calculated and based on a threshold, speaker authenticity is established.