ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Considering speech quality in speaker verification fusion

Yosef A. Solewicz, Moshe Koppel

This paper emphasizes the benefits of embedding data categorization within fusion of classifiers for text-independent speaker verification. A selective fusion framework is presented which considers data idiosyncrasies by assigning particular test samples to appropriate fusion schemes. As an extension, incompatible data can be spotted and excluded from inherent classification errors. In addition, it's shown that multi-resolution low-level classifiers successfully boost fusion capabilities in noise.

doi: 10.21437/Interspeech.2005-646

Cite as: Solewicz, Y.A., Koppel, M. (2005) Considering speech quality in speaker verification fusion. Proc. Interspeech 2005, 2189-2192, doi: 10.21437/Interspeech.2005-646

  author={Yosef A. Solewicz and Moshe Koppel},
  title={{Considering speech quality in speaker verification fusion}},
  booktitle={Proc. Interspeech 2005},