Conference paper

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.
Publication language:english
Original title:BUT Neural Network Features for Spontaneous Vietnamese in BABEL
Title (cs):VUT příznaky založené na nuronových sítích pro rozpoznávání spontánní vietnamštiny v programu BABEL
Proceedings:Proceedings of ICASSP 2014
Conference:The 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Place:Florencie, IT
Publisher:IEEE Signal Processing Society
speech recognition, discriminative training, bottleneck neural networks, adaptation of neural networks, regiondependent transforms
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.
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.
   author = {Martin Karafi{\'{a}}t and Franti{\v{s}}ek
	Gr{\'{e}}zl and Mirko Hannemann and Jan
   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 = {}

Your IPv4 address:
Switch to https