Detail publikace

Adaptation of Multilingual Stacked Bottle-neck Neural Network Structure for New Language

Originální název

Adaptation of Multilingual Stacked Bottle-neck Neural Network Structure for New Language

Anglický název

Adaptation of Multilingual Stacked Bottle-neck Neural Network Structure for New Language

Jazyk

en

Originální abstrakt

In this paper a multilingual training of Stacked Bottle- Neck neural network structure for feature extraction is addressed. While for languages with plentiful resources, the optimal approach is to train the BN-NN on the target data, limited resources call for re-using data from other languages.

Anglický abstrakt

In this paper a multilingual training of Stacked Bottle- Neck neural network structure for feature extraction is addressed. While for languages with plentiful resources, the optimal approach is to train the BN-NN on the target data, limited resources call for re-using data from other languages.

BibTex


@inproceedings{BUT111544,
  author="František {Grézl} and Martin {Karafiát} and Karel {Veselý}",
  title="Adaptation of Multilingual Stacked Bottle-neck Neural Network Structure for New Language",
  annote="In this paper a multilingual training of Stacked Bottle- Neck neural network
structure for feature extraction is addressed. While for languages with plentiful
resources, the optimal approach is to train the BN-NN on the target data, limited
resources call for re-using data from other languages.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of ICASSP 2014",
  chapter="111544",
  doi="10.1109/ICASSP.2014.6855089",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2014",
  month="may",
  pages="7704--7708",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}