Článek ve sborníku konference

NOVOTNÝ Ondřej, MATĚJKA Pavel, GLEMBEK Ondřej, PLCHOT Oldřich, GRÉZL František, BURGET Lukáš a ČERNOCKÝ Jan. Analysis of the DNN-Based SRE Systems in Multi-language Conditions. In: Proceedings of SLT 2016. San Diego: IEEE Signal Processing Society, 2016, s. 199-204. ISBN 978-1-5090-4903-5. Dostupné z: http://ieeexplore.ieee.org/document/7846265/
Jazyk publikace:angličtina
Název publikace:Analysis of the DNN-Based SRE Systems in Multi-language Conditions
Název (cs):Analýza systémů pro rozpoznávání mluvčího založených na DNN v multi-lingválních podmínkách
Strany:199-204
Sborník:Proceedings of SLT 2016
Konference:2016 IEEE Workshop on Spoken Language Technology
Místo vydání:San Diego, US
Rok:2016
URL:http://ieeexplore.ieee.org/document/7846265/
ISBN:978-1-5090-4903-5
DOI:10.1109/slt.2016.7846265
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2016/novotny_slt2016_0000199.pdf [PDF]
Klíčová slova
DNN, Multi-Language, Speaker Recognition
Anotace
Článek pojednává o analýze systémů pro rozpoznávání mluvčího založených na DNN v multi-lingválních podmínkách.
Abstrakt
This paper analyzes the behavior of our state-of-the-art Deep Neural Network/i-vector/PLDA-based speaker recognition systems in multi-language conditions. On the "Language Pack" of the PRISM set, we evaluate the systems performance using the NISTs standard metrics. We show that not only the gain from using DNNs vanishes, nor using dedicated DNNs for target conditions helps, but also the DNN-based systems tend to produce de-calibrated scores under the studied conditions. This work gives suggestions for directions of future research rather than any particular solutions to these issues.
BibTeX:
@INPROCEEDINGS{
   author = {Ond{\v{r}}ej Novotn{\'{y}} and Pavel Mat{\v{e}}jka
	and Ond{\v{r}}ej Glembek and Old{\v{r}}ich Plchot
	and Franti{\v{s}}ek Gr{\'{e}}zl and
	Luk{\'{a}}{\v{s}} Burget and Jan
	{\v{C}}ernock{\'{y}}},
   title = {Analysis of the DNN-Based SRE Systems in
	Multi-language Conditions},
   pages = {199--204},
   booktitle = {Proceedings of SLT 2016},
   year = 2016,
   location = {San Diego, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-5090-4903-5},
   doi = {10.1109/slt.2016.7846265},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=11309}
}

Vaše IPv4 adresa: 18.232.53.231
Přepnout na https