Publication detail

BUT Neural Network Features for Spontaneous Vietnamese in BABEL

KARAFIÁT, M. GRÉZL, F. HANNEMANN, M. ČERNOCKÝ, J.

Original Title

BUT Neural Network Features for Spontaneous Vietnamese in BABEL

Type

conference paper

Language

English

Original Abstract

The paper deals with multiple facets of NN feature extraction training. Not surprisingly, we found that data preparation is crucial for the success of NN training. In case we dispose of data from other (well represented) languages, we should go for it as we have shown that multilingual fine-tuning outperforms unsupervised training.

Keywords

speech recognition, discriminative training, bottleneck neural networks, adaptation of neural networks, regiondependent transforms

Authors

KARAFIÁT, M.; GRÉZL, F.; HANNEMANN, M.; ČERNOCKÝ, J.

RIV year

2014

Released

4. 5. 2014

Publisher

IEEE Signal Processing Society

Location

Florencie

ISBN

978-1-4799-2892-7

Book

Proceedings of ICASSP 2014

Pages from

5659

Pages to

5663

Pages count

5

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2014/karafiat_icassp2014_p5659.pdf

BibTex

@inproceedings{BUT111541,
  author="Martin {Karafiát} and František {Grézl} and Mirko {Hannemann} and Jan {Černocký}",
  title="BUT Neural Network Features for Spontaneous Vietnamese in BABEL",
  booktitle="Proceedings of ICASSP 2014",
  year="2014",
  pages="5659--5663",
  publisher="IEEE Signal Processing Society",
  address="Florencie",
  doi="10.1109/ICASSP.2014.6854679",
  isbn="978-1-4799-2892-7",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2014/karafiat_icassp2014_p5659.pdf"
}