English

Speaker recognition improvement using blind inversion of distortions

Sound 2022-03-03 v1 Machine Learning Audio and Speech Processing

Abstract

In this paper we propose the inversion of nonlinear distortions in order to improve the recognition rates of a speaker recognizer system. We study the effect of saturations on the test signals, trying to take into account real situations where the training material has been recorded in a controlled situation but the testing signals present some mismatch with the input signal level (saturations). The experimental results shows that a combination of data fusion with and without nonlinear distortion compensation can improve the recognition rates with saturated test sentences from 80% to 88.57%, while the results with clean speech (without saturation) is 87.76% for one microphone.

Keywords

Cite

@article{arxiv.2203.01164,
  title  = {Speaker recognition improvement using blind inversion of distortions},
  author = {Marcos Faundez-Zanuy and Jordi Sole-Casals},
  journal= {arXiv preprint arXiv:2203.01164},
  year   = {2022}
}

Comments

4 pages

R2 v1 2026-06-24T09:59:27.676Z