Journal article

FÉR Radek, MATĚJKA Pavel, GRÉZL František, PLCHOT Oldřich, VESELÝ Karel and ČERNOCKÝ Jan. Multilingually Trained Bottleneck Features in Spoken Language Recognition. Computer Speech and Language. Amsterdam: Elsevier Science, 2017, vol. 2017, no. 46, pp. 252-267. ISSN 0885-2308. Available from: http://www.sciencedirect.com/science/article/pii/S0885230816302947
Publication language:english
Original title:Multilingually Trained Bottleneck Features in Spoken Language Recognition
Title (cs):Vícejazyčně trénované parametry založené na úzkém hrdle neuronových sítí pro rozpoznávání mluveného jazyka
Pages:252-267
Place:NL
Year:2017
URL:http://www.sciencedirect.com/science/article/pii/S0885230816302947
Journal:Computer Speech and Language, Vol. 2017, No. 46, Amsterdam, NL
ISSN:0885-2308
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2017/fer_CSL2017.pdf [PDF]
Files: 
+Type Name Title Size Last modified
iconfer_CSL2017.pdf848 KB2017-09-07 12:01:54
^ Select all
With selected:
Keywords
Multilingual training, Bottleneck features, Spoken language recognition
Annotation
Multilingual training of neural networks has proven to be simple yet effective way to deal with multilingual training corpora. It allows to use several resources to jointly train a language independent representation of features, which can be encoded into low-dimensional feature set by embedding narrow bottleneck layer to the network. In this paper, we analyze such features on the task of spoken language recognition (SLR), focusing on practical aspects of training bottleneck networks and analyzing their integration in SLR. By comparing properties of mono and multilingual features we show the suitability of multilingual training for SLR. The state-of-the-art performance of these features is demonstrated on the NIST LRE09 database.
Abstract
Multilingual training of neural networks has proven to be simple yet effective way to deal with multilingual training corpora. It allows to use several resources to jointly train a language independent representation of features, which can be encoded into low-dimensional feature set by embedding narrow bottleneck layer to the network. In this paper, we analyze such features on the task of spoken language recognition (SLR), focusing on practical aspects of training bottleneck networks and analyzing their integration in SLR. By comparing properties of mono and multilingual features we show the suitability of multilingual training for SLR. The state-of-the-art performance of these features is demonstrated on the NIST LRE09 database.
BibTeX:
@ARTICLE{
   author = {Radek F{\'{e}}r and Pavel Mat{\v{e}}jka and Franti{\v{s}}ek
	Gr{\'{e}}zl and Old{\v{r}}ich Plchot and Karel Vesel{\'{y}}
	and Jan {\v{C}}ernock{\'{y}}},
   title = {Multilingually Trained Bottleneck Features in Spoken
	Language Recognition},
   pages = {252--267},
   journal = {Computer Speech and Language},
   volume = {2017},
   number = {46},
   year = {2017},
   ISSN = {0885-2308},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11518}
}

Your IPv4 address: 54.224.49.217
Switch to IPv6 connection

DNSSEC [dnssec]