Detail publikace

Alternative Approaches to Neural Network based Speaker Verification

SILNOVA, A. BURGET, L. ČERNOCKÝ, J.

Originální název

Alternative Approaches to Neural Network based Speaker Verification

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper describes experiment with the standard ivector/ PLDA system trained on the different NN based features. The results are reported on female part of NIST SRE 2010, condition 5 (English telephone data).

Klíčová slova

automatic speaker recognition, deep neural networks, bottleneck features

Autoři

SILNOVA, A.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

20. 8. 2017

Nakladatel

International Speech Communication Association

Místo

Stockholm

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2017

Číslo

08

Stát

Francouzská republika

Strany od

1572

Strany do

1575

Strany počet

4

URL

http://www.isca-speech.org/archive/Interspeech_2017/pdfs/1062.PDF

BibTex

@inproceedings{BUT144491,
  author="Anna {Silnova} and Lukáš {Burget} and Jan {Černocký}",
  title="Alternative Approaches to Neural Network based Speaker Verification",
  booktitle="Proceedings of Interspeech 2017",
  year="2017",
  journal="Proceedings of Interspeech",
  volume="2017",
  number="08",
  pages="1572--1575",
  publisher="International Speech Communication Association",
  address="Stockholm",
  doi="10.21437/Interspeech.2017-1062",
  issn="1990-9772",
  url="http://www.isca-speech.org/archive/Interspeech_2017/pdfs/1062.PDF"
}