Publication Details

BUT Neural Network Features for Spontaneous Vietnamese in BABEL

KARAFIÁT Martin, GRÉZL František, HANNEMANN Mirko and ČERNOCKÝ Jan. BUT Neural Network Features for Spontaneous Vietnamese in BABEL. In: Proceedings of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014, pp. 5659-5663. ISBN 978-1-4799-2892-7.
Czech title
VUT příznaky založené na nuronových sítích pro rozpoznávání spontánní vietnamštiny v programu BABEL
Type
conference paper
Language
english
Authors
URL
Keywords

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

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.

Annotation

This paper presents our work on speech recognition of Vietnamese spontaneous telephone conversations. It focuses on feature extraction by Stacked Bottle-Neck neural networks: several improvements such as semi-supervised training on untranscribed data, increasing of precision of state targets, and CMLLR adaptations were investigated. We have also tested speaker adaptive training of this architecture and significant gain was found. The results are reported on BABEL Vietnamese data.

Published
2014
Pages
5659-5663
Proceedings
Proceedings of ICASSP 2014
Conference
The 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Florencie, IT
ISBN
978-1-4799-2892-7
Publisher
IEEE Signal Processing Society
Place
Florencie, IT
DOI
UT WoS
000343655305131
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB10554,
   author = "Martin Karafi\'{a}t and Franti\v{s}ek Gr\'{e}zl and Mirko Hannemann and Jan \v{C}ernock\'{y}",
   title = "BUT Neural Network Features for Spontaneous Vietnamese in BABEL",
   pages = "5659--5663",
   booktitle = "Proceedings of ICASSP 2014",
   year = 2014,
   location = "Florencie, IT",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4799-2892-7",
   doi = "10.1109/ICASSP.2014.6854679",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10554"
}
Back to top