Publication detail

Pairwise Discriminative Speaker Verification in the I -Vector Space

CUMANI, S. BRUMMER, J. BURGET, L. LAFACE, P. PLCHOT, O. VASILAKAKIS, V.

Original Title

Pairwise Discriminative Speaker Verification in the I -Vector Space

Type

journal article - other

Language

English

Original Abstract

In this work we present a novel framework for discriminative training of speaker verification systems, where a trial is represented, as in the PLDA approach, by an i-vector pair, and the task is discrimination between same-speaker and dif- ferent-speaker classes. This pairwise SVM approach provides a more natural paradigm to speaker verification compared to the classical one-vs-all discriminative training.

Keywords

Discriminative training, I-vector, large-scale training, probabilistic linear discriminant analysis, speaker recog- nition, support vector machines

Authors

CUMANI, S.; BRUMMER, J.; BURGET, L.; LAFACE, P.; PLCHOT, O.; VASILAKAKIS, V.

RIV year

2013

Released

20. 2. 2013

ISBN

1558-7916

Periodical

IEEE Transactions on Audio, Speech, and Language Processing

Year of study

2013

Number

6

State

United States of America

Pages from

1217

Pages to

1227

Pages count

11

URL

https://ieeexplore.ieee.org/abstract/document/6466371

BibTex

@article{BUT103568,
  author="Sandro {Cumani} and Johan Nikolaas Langenhoven {Brummer} and Lukáš {Burget} and Pietro {Laface} and Oldřich {Plchot} and Vasileios {Vasilakakis}",
  title="Pairwise Discriminative Speaker Verification in the I -Vector Space",
  journal="IEEE Transactions on Audio, Speech, and Language Processing",
  year="2013",
  volume="2013",
  number="6",
  pages="1217--1227",
  doi="10.1109/TASL.2013.2245655",
  issn="1558-7916",
  url="https://ieeexplore.ieee.org/abstract/document/6466371"
}