Detail publikace

The Language-Independent Bottleneck Features

Originální název

The Language-Independent Bottleneck Features

Anglický název

The Language-Independent Bottleneck Features

Jazyk

en

Originální abstrakt

The paper is about language-independent bottleneck features, which are generated by Multi-lingual Neural Network. This leads to features which are not biased towards any of the source languages, making the features effectively language independent.

Anglický abstrakt

The paper is about language-independent bottleneck features, which are generated by Multi-lingual Neural Network. This leads to features which are not biased towards any of the source languages, making the features effectively language independent.

BibTex


@inproceedings{BUT97015,
  author="Karel {Veselý} and Martin {Karafiát} and František {Grézl} and Miloš {Janda} and Ekaterina {Egorova}",
  title="The Language-Independent Bottleneck Features",
  annote="The paper is about language-independent bottleneck features, which are generated
by Multi-lingual Neural Network. This leads to features which are not biased
towards any of the source languages, making the features effectively language
independent.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of IEEE 2012 Workshop on Spoken Language Technology",
  chapter="97015",
  doi="10.1109/SLT.2012.6424246",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2012",
  month="december",
  pages="336--341",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}