Two-stage decision making algorithm for speaker verification


Yaparoglu E. T., ŞENOL Y.

IEEE 14th Signal Processing and Communications Applications, Antalya, Turkey, 16 - 19 April 2006, pp.57-58 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu.2006.1659841
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.57-58
  • Dokuz Eylül University Affiliated: Yes

Abstract

A new decision making algorithm in speaker verification is presented. First, a baseline system is formed using mel-frequency cepstral coefficients (MFCC) as features, and for speaker modeling a radial basis function (RBF) neural network is used. Then, a two-stage decision making algorithm is proposed, which has the aim to eliminate the qualified impostors in the second stage.