Nonlinear predictive models: overview and possibilities in speaker recognition

  • Authors:
  • Marcos Faundez-Zanuy;Mohamed Chetouani

  • Affiliations:
  • Escola Universitària Politècnica de Mataró, Barcelona, Spain;Université Pierre and Marie Curie, Paris VI, France

  • Venue:
  • Progress in nonlinear speech processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we give a brief overview of speaker recognition with special emphasis on nonlinear predictive models, based on neural nets. Main challenges and possibilities for nonlinear feature extraction are described, and experimental results of several strategies are provided. This paper is presented as a starting point for the non-linear model for speaker recognition.