Publication Details

Comparison of Scoring Methods used in Speaker Recognition with Joint Factor Analysis

GLEMBEK, O.; BURGET, L.; DEHAK, N.; BRÜMMER, N.; KENNY, P. Comparison of Scoring Methods used in Speaker Recognition with Joint Factor Analysis. Proc. ICASSP 2009. Taipei: IEEE Signal Processing Society, 2009. p. 1-4. ISBN: 978-1-4244-2354-5.
Czech title
Srovnání skórovacích metod pro rozpoznávání řečníka s Joint Factor Analysis
Type
conference paper
Language
English
Authors
Glembek Ondřej, Ing., Ph.D.
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Dehak Najim
Brümmer Niko
Kenny Patrick
URL
Keywords

GMM, fast scoring, speaker recognition, joint factor analysis

Abstract

The paper describes the Comparison of Scoring Methods used in Speaker Recognition with Joint Factor Analysis (JFA).

Annotation

The aim of this paper is to compare different log-likelihood scoring methods, that different sites used in the latest state-of-the-art Joint Factor Analysis (JFA) Speaker Recognition systems. The algorithms use various assumptions and have been derived from various approximations of the objective functions of JFA. We compare the techniques in terms of speed and performance. We show, that approximations of the true log-likelihood ratio (LLR) may lead to significant speedup without any loss in performance.

Published
2009
Pages
1–4
Proceedings
Proc. ICASSP 2009
ISBN
978-1-4244-2354-5
Publisher
IEEE Signal Processing Society
Place
Taipei
BibTeX 
@inproceedings{BUT30226,
  author="Ondřej {Glembek} and Lukáš {Burget} and Najim {Dehak} and Niko {Brümmer} and Patrick {Kenny}",
  title="Comparison of Scoring Methods used in Speaker Recognition with Joint Factor Analysis",
  booktitle="Proc. ICASSP 2009",
  year="2009",
  pages="1--4",
  publisher="IEEE Signal Processing Society",
  address="Taipei",
  isbn="978-1-4244-2354-5",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2009/glembek_icassp2009.pdf"
}
Back to top