Publication detail

Fast Discriminative Speaker Verification in the I-Vector Space

CUMANI, S. BRÜMMER, N. BURGET, L. LAFACE, P.

Original Title

Fast Discriminative Speaker Verification in the I-Vector Space

English Title

Fast Discriminative Speaker Verification in the I-Vector Space

Type

conference paper

Language

en

Original Abstract

A fast discriminative training approach for speaker verification based on i-vectors has been presented. On NIST telephone evaluation data, the resulting models perform better, without the need for normalization techniques, than the generative ones, even compared with heavy-tailed models.

English abstract

A fast discriminative training approach for speaker verification based on i-vectors has been presented. On NIST telephone evaluation data, the resulting models perform better, without the need for normalization techniques, than the generative ones, even compared with heavy-tailed models.

Keywords

Discriminative Training,Two-covariance Kernel, Support Vector Machines, i-vectors

RIV year

2011

Released

22.05.2011

Publisher

IEEE Signal Processing Society

Location

Praha

ISBN

978-1-4577-0537-3

Book

Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

4852

Pages to

4855

Pages count

4

URL

Documents

BibTex


@inproceedings{BUT76385,
  author="Sandro {Cumani} and Niko {Brümmer} and Lukáš {Burget} and Pietro {Laface}",
  title="Fast Discriminative Speaker Verification in the I-Vector Space",
  annote="A fast discriminative training approach for speaker verification based on
i-vectors has been presented. On NIST telephone evaluation data, the resulting
models perform better, without the need for normalization techniques, than the
generative ones, even compared with heavy-tailed models.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011",
  chapter="76385",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2011",
  month="may",
  pages="4852--4855",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}