ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Effective estimation of a multi-session speaker model using information on signal parameters

Konstantin Simonchik, Andrey Shulipa, Timur Pekhovsky

The paper deals with the problem of estimation an optimal i-vector based speaker voice model using several sessions of his or her voice recordings, each of which has different signal parameters: speech duration and SNR. Our aim is to minimize inter-session variability so as to achieve minimal EER in the task of speaker recognition. We examine the influence of the main signal parameters on intersession variability and propose a model for multi-session i-vector estimation based on minimizing inter-session variability.


doi: 10.21437/Interspeech.2013-403

Cite as: Simonchik, K., Shulipa, A., Pekhovsky, T. (2013) Effective estimation of a multi-session speaker model using information on signal parameters. Proc. Interspeech 2013, 1604-1608, doi: 10.21437/Interspeech.2013-403

@inproceedings{simonchik13_interspeech,
  author={Konstantin Simonchik and Andrey Shulipa and Timur Pekhovsky},
  title={{Effective estimation of a multi-session speaker model using information on signal parameters}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={1604--1608},
  doi={10.21437/Interspeech.2013-403}
}