Detail publikace

Multilingually Trained Bottleneck Features in Spoken Language Recognition

FÉR, R. MATĚJKA, P. GRÉZL, F. PLCHOT, O. VESELÝ, K. ČERNOCKÝ, J.

Originální název

Multilingually Trained Bottleneck Features in Spoken Language Recognition

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Multilingual training, Bottleneck features, Spoken language recognition

Autoři

FÉR, R.; MATĚJKA, P.; GRÉZL, F.; PLCHOT, O.; VESELÝ, K.; ČERNOCKÝ, J.

Vydáno

25. 7. 2017

ISSN

0885-2308

Periodikum

COMPUTER SPEECH AND LANGUAGE

Ročník

2017

Číslo

46

Stát

Spojené království Velké Británie a Severního Irska

Strany od

252

Strany do

267

Strany počet

16

URL

BibTex

@article{BUT144471,
  author="Radek {Fér} and Pavel {Matějka} and František {Grézl} and Oldřich {Plchot} and Karel {Veselý} and Jan {Černocký}",
  title="Multilingually Trained Bottleneck Features in Spoken Language Recognition",
  journal="COMPUTER SPEECH AND LANGUAGE",
  year="2017",
  volume="2017",
  number="46",
  pages="252--267",
  doi="10.1016/j.csl.2017.06.008",
  issn="0885-2308",
  url="http://www.sciencedirect.com/science/article/pii/S0885230816302947"
}