Detail publikace

Study of Probabilistic and Bottle-Neck Features in Multilingual Environment

Originální název

Study of Probabilistic and Bottle-Neck Features in Multilingual Environment

Anglický název

Study of Probabilistic and Bottle-Neck Features in Multilingual Environment

Jazyk

en

Originální abstrakt

The article studies properties of features obtained using neural networks in milti=lingual recognition systems. The neural networks are trained on particular data and thus it is interesting to observe bahavior of these features when used on data from different language.

Anglický abstrakt

The article studies properties of features obtained using neural networks in milti=lingual recognition systems. The neural networks are trained on particular data and thus it is interesting to observe bahavior of these features when used on data from different language.

BibTex


@inproceedings{BUT76454,
  author="František {Grézl} and Martin {Karafiát} and Miloš {Janda}",
  title="Study of Probabilistic and Bottle-Neck Features in Multilingual Environment",
  annote="The article studies properties of features obtained using neural networks in
milti=lingual recognition systems. The neural networks are trained on particular
data and thus it is interesting to observe bahavior of these features when used
on data from different language.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of ASRU 2011",
  chapter="76454",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2011",
  month="december",
  pages="359--364",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}