Speaker Verification on Unbalanced Data with Genetic Programming

  • Róisín Loughran
  • Alexandros Agapitos
  • Ahmed Kattan
  • Anthony Brabazon
  • Michael O’Neill
Conference paper

DOI: 10.1007/978-3-319-31204-0_47

Volume 9597 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Loughran R., Agapitos A., Kattan A., Brabazon A., O’Neill M. (2016) Speaker Verification on Unbalanced Data with Genetic Programming. In: Squillero G., Burelli P. (eds) Applications of Evolutionary Computation. EvoApplications 2016. Lecture Notes in Computer Science, vol 9597. Springer, Cham

Abstract

Automatic Speaker Verification (ASV) is a highly unbalanced binary classification problem, in which any given speaker must be verified against everyone else. We apply Genetic programming (GP) to this problem with the aim of both prediction and inference. We examine the generalisation of evolved programs using a variety of fitness functions and data sampling techniques found in the literature. A significant difference between train and test performance, which can indicate overfitting, is found in the evolutionary runs of all to-be-verified speakers. Nevertheless, in all speakers, the best test performance attained is always superior than just merely predicting the majority class. We examine which features are used in good-generalising individuals. The findings can inform future applications of GP or other machine learning techniques to ASV about the suitability of feature-extraction techniques.

Keywords

Speaker verification Unbalanced data Genetic programming Feature selection 

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Róisín Loughran
    • 1
  • Alexandros Agapitos
    • 1
  • Ahmed Kattan
    • 2
  • Anthony Brabazon
    • 1
  • Michael O’Neill
    • 1
  1. 1.Natural Computing Research and Applications GroupUniversity College DublinDublinIreland
  2. 2.Computer Science DepartmentUm Al-Qura UniversityMeccaSaudi Arabia