Článek ve sborníku konference

LOPEZ-MORENO Ignacio, GONZALEZ-DOMINGUEZ Javier, MARTÍNEZ González David, PLCHOT Oldřich, GONZALEZ-RODRIGUEZ Joaquin a MORENO Pedro. Automatic Language Identification Using Deep Neural Networks. In: Proceeding of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014, s. 5374-5378. ISBN 978-1-4799-2892-7.
Jazyk publikace:angličtina
Název publikace:Automatic Language Identification Using Deep Neural Networks
Název (cs):Automatická identifikace mluvčího pomocí hlubokých neuronových sítí
Strany:5374-5378
Sborník:Proceeding of ICASSP 2014
Konference:The 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Místo vydání:Florencie, IT
Rok:2014
ISBN:978-1-4799-2892-7
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2014/lopez_moreno_icassp2014_p5374.pdf [PDF]
Klíčová slova
Automatic Language Identification, ivectors, DNNs
Anotace
V tomto článku jsme experimentovali s použitím hlubokých neuronových sítí (DNNs) pro automatickou identifikaci mluvčího (LID).
Abstrakt
This work studies the use of deep neural networks (DNNs) to address automatic language identification (LID). Motivated by their recent success in acoustic modelling, we adapt DNNs to the problem of identifying the language of a given spoken utterance from short-term acoustic features. The proposed approach is compared to state-of-the-art i-vector based acoustic systems on two different datasets: Google 5M LID corpus and NIST LRE 2009. Results show how LID can largely benefit from using DNNs, especially when a large amount of training data is available. We found relative improvements up to 70%, in Cavg, over the baseline system.
BibTeX:
@INPROCEEDINGS{
   author = {Ignacio Lopez-Moreno and Javier Gonzalez-Dominguez
	and David Gonz{\'{a}}lez Mart{\'{i}}nez and
	Old{\v{r}}ich Plchot and Joaquin
	Gonzalez-Rodriguez and Pedro Moreno},
   title = {Automatic Language Identification Using Deep
	Neural Networks},
   pages = {5374--5378},
   booktitle = {Proceeding of ICASSP 2014},
   year = {2014},
   location = {Florencie, IT},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4799-2892-7},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=10562}
}

Vaše IPv4 adresa: 107.23.176.162
Přepnout na https

DNSSEC [dnssec]