Domain Adaptation Via Within-class Covariance Correction in I-Vector Based Speaker Recognition Systerms
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F14%3APU111948" target="_blank" >RIV/00216305:26230/14:PU111948 - isvavai.cz</a>
Result on the web
<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=10555" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=10555</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2014.6854359" target="_blank" >10.1109/ICASSP.2014.6854359</a>
Alternative languages
Result language
angličtina
Original language name
Domain Adaptation Via Within-class Covariance Correction in I-Vector Based Speaker Recognition Systerms
Original language description
In this paper, we have shown a technique of within-class correction for Linear Discriminant Analysis estimation. We have shown that when correct dataset clustering is used, adapting the within-class covariance of LDA by low-rank between-dataset covariance matrix can lead to significant improvement of the system, namely up to 70% in the Domain Adaptation Task, and 17.5% and 36% relative in the RATS unmatched and semi-matched tasks, respectively. The dataset clustering problem gave us an interesting direction for future research.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of ICASSP 2014
ISBN
978-1-4799-2892-7
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
4060-4064
Publisher name
IEEE Signal Processing Society
Place of publication
Florencie
Event location
Florencie
Event date
May 4, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000343655304011