Detail publikačního výsledku

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

GRÉZL, F.; KARAFIÁT, M.; VESELÝ, K.

Original Title

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

English Title

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

Type

Paper in proceedings (conference paper)

Original Abstract

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

English abstract

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

Keywords

feature extraction, Bottle-neck features, neuralnetwork adaptation, multilingual neural networks, Stacked Bottle-Neck structure

Key words in English

feature extraction, Bottle-neck features, neuralnetwork adaptation, multilingual neural networks, Stacked Bottle-Neck structure

Authors

GRÉZL, F.; KARAFIÁT, M.; VESELÝ, K.

RIV year

2015

Released

04.05.2014

Publisher

IEEE Signal Processing Society

Location

Florencie

ISBN

978-1-4799-2892-7

Book

Proceedings of ICASSP 2014

Pages from

7704

Pages to

7708

Pages count

5

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2014/grezl_icassp2014_p7704_adapation.pdf

Full text in the Digital Library

http://hdl.handle.net/

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",
  booktitle="Proceedings of ICASSP 2014",
  year="2014",
  pages="7704--7708",
  publisher="IEEE Signal Processing Society",
  address="Florencie",
  doi="10.1109/ICASSP.2014.6855089",
  isbn="978-1-4799-2892-7",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2014/grezl_icassp2014_p7704_adapation.pdf"
}