Faculty of Information Technology, BUT

Publication Details

Exploring ANN Back-Ends for i-Vector Based Speaker Age Estimation

SILNOVA Anna, GLEMBEK Ondřej, KINNUNEN Tomi and MATĚJKA Pavel. Exploring ANN Back-Ends for i-Vector Based Speaker Age Estimation. In: Proceedings of Interspeech 2015. Dresden: International Speech Communication Association, 2015, pp. 3036-3040. ISBN 978-1-5108-1790-6. ISSN 1990-9772.
Czech title
Využití ANN klasifikátorů pro odhad věku řečníka založený na i-vektorech
Type
conference paper
Language
english
Authors
Silnova Anna, MSc. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Kinnunen Tomi (University of Eastern Finland)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords
age estimation, i-vector, multilayer perceptron
Abstract
This publication focuses on exploring artificial neural net (ANN) Back-Ends for i-Vector Based Speaker Age Estimation.
Annotation
We address the problem of speaker age estimation using ivectors. We first compare different i-vector extraction setups and then focus on (shallow) artificial neural net (ANN) backends. We explore ANN architecture, training algorithm and ANN ensembles. The results on NIST 2008 and 2010 SRE data indicate that, after extensive parameter optimization, ANN back-end in combination with i-vectors reaches mean absolute errors (MAEs) of 5.49 (females) and 6.35 (males), which are 4.5% relative improvement in comparison to our support-vector regression (SVR) baseline. Hence, the choice of back-end did not affect the accuracy much; a suggested future direction is therefore focusing more on front-end processing.
Published
2015
Pages
3036-3040
Journal
Proceedings of Interspeech, vol. 2015, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2015
Conference
INTERSPEECH 2015, Dresden, DE
ISBN
978-1-5108-1790-6
Publisher
International Speech Communication Association
Place
Dresden, DE
BibTeX
@INPROCEEDINGS{FITPUB10971,
   author = "Anna Silnova and Ond\v{r}ej Glembek and Tomi Kinnunen and Pavel Mat\v{e}jka",
   title = "Exploring ANN Back-Ends for i-Vector Based Speaker Age Estimation",
   pages = "3036--3040",
   booktitle = "Proceedings of Interspeech 2015",
   journal = "Proceedings of Interspeech",
   volume = 2015,
   number = 09,
   year = 2015,
   location = "Dresden, DE",
   publisher = "International Speech Communication Association",
   ISBN = "978-1-5108-1790-6",
   ISSN = "1990-9772",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10971"
}
Back to top