Result Details

Probabilistic Linear Discriminant Analysis Of I-Vector Posterior Distributions

CUMANI, S.; PLCHOT, O.; LAFACE, P. Probabilistic Linear Discriminant Analysis Of I-Vector Posterior Distributions. Proceedings of ICASSP 2013. Vancouver: IEEE Signal Processing Society, 2013. p. 7644-7648. ISBN: 978-1-4799-0355-9.
Type
conference paper
Language
English
Authors
Cumani Sandro, Ph.D.
Plchot Oldřich, Ing., Ph.D., DCGM (FIT)
Laface Pietro
Abstract

This article describes Probabilistic Linear Discriminant Analysis Of I-Vector Posterior Distributions.

Keywords

Speaker recognition, i-vector, PLDA

URL
Annotation

The i-vector extraction process is affected by several factors such as the noise level, the acoustic content of the observed features, and the duration of the analyzed speech segment. These factors influence both the i-vector estimate and its uncertainty, represented by the i- vector posterior covariance. This paper present a new PLDA model that, unlike the standard one, exploits the intrinsic i-vector uncertainty. Since short segments are known to decrease recognition accuracy, and segment duration is the main factor affecting the i-vector covariance, we designed a set of experiments aiming at comparing the standard and the new PLDA models on short speech cuts of variable duration, randomly extracted from the conversations included in the NIST SRE 2010 female telephone extended core condition. Our results show that the new model outperforms the standard PLDA when tested on short segments, and keeps the accuracy of the latter for long enough utterances. In particular, the relative improvement is up to 13% for the EER, 5% for DCF08, and 2.5% for DCF10.

Published
2013
Pages
7644–7648
Proceedings
Proceedings of ICASSP 2013
Conference
38th International Conference on Acoustics, Speech, and Signal Processing
ISBN
978-1-4799-0355-9
Publisher
IEEE Signal Processing Society
Place
Vancouver
BibTeX 
@inproceedings{BUT103483,
  author="Sandro {Cumani} and Oldřich {Plchot} and Pietro {Laface}",
  title="Probabilistic Linear Discriminant Analysis Of I-Vector Posterior Distributions",
  booktitle="Proceedings of ICASSP 2013",
  year="2013",
  pages="7644--7648",
  publisher="IEEE Signal Processing Society",
  address="Vancouver",
  isbn="978-1-4799-0355-9",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/cumani_icassp2013_0007644.pdf"
}
Projects
Centrum excelence IT4Innovations, MŠMT, Operační program Výzkum a vývoj pro inovace, ED1.1.00/02.0070, start: 2011-01-01, end: 2015-12-31, completed
DARPA Robust Automatic Transcription of Speech (RATS) - RATS Patrol I, BBN, start: 2010-09-23, end: 2014-06-30, completed
Security-Oriented Research in Information Technology, MŠMT, Institucionální prostředky SR ČR (např. VZ, VC), MSM0021630528, start: 2007-01-01, end: 2013-12-31, running
Support of Interdisciplinary Excellence Research Teams Establishment at BUT, EU, OP VK - Oblast podpory 2.3 - Lidské zdroje ve VaV, EE2.3.30.0005, start: 2012-07-01, end: 2015-06-30, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top