Result Details

Multilingual Region-Dependent Transforms

KARAFIÁT, M.; BURGET, L.; GRÉZL, F.; VESELÝ, K.; ČERNOCKÝ, J. Multilingual Region-Dependent Transforms. In Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016. Shanghai: IEEE Signal Processing Society, 2016. p. 5430-5434. ISBN: 978-1-4799-9988-0.
Type
conference paper
Language
English
Authors
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Grézl František, Ing., Ph.D., DCGM (FIT)
Veselý Karel, Ing., Ph.D., DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Abstract

This paper presented our further steps in the development of a featureextraction scheme easily transferable to a new language withseverely limited training data.

Keywords

Automatic speech recognition, Region-DependentTransforms, Multilingual speech recognition, Feedforward neuralnetworks

URL
Annotation

In recent years, trained feature extraction (FE) schemes based on neural networks have replaced or complemented traditional approaches in top performing systems. This paper deals with FE in multilingual scenarios with a target language with low amount of transcribed data. Continuing our previous work on multilingual training of Stacked Bottle-Neck Neural Network FE schemes, we concentrate on improving the discriminatively trained Region- Dependent Transforms. We show that multilingual training of RDT can be implemented by merging statistics from several languages. In our case we used up to 11 source languages to build a FE which generalize well for a new language. This allows us to build a strong bootstrapping model for the final ASR system. The results are produced on IARPA Babel data.

Published
2016
Pages
5430–5434
Proceedings
Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016
Conference
41th IEEE International Conference on Acoustics, Speech and Signal Processing
ISBN
978-1-4799-9988-0
Publisher
IEEE Signal Processing Society
Place
Shanghai
DOI
10.1109/ICASSP.2016.7472715
UT WoS
000388373405116
EID Scopus
2-s2.0-84973315947
BibTeX 
@inproceedings{BUT130965,
  author="Martin {Karafiát} and Lukáš {Burget} and František {Grézl} and Karel {Veselý} and Jan {Černocký}",
  title="Multilingual Region-Dependent Transforms",
  booktitle="Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016",
  year="2016",
  pages="5430--5434",
  publisher="IEEE Signal Processing Society",
  address="Shanghai",
  doi="10.1109/ICASSP.2016.7472715",
  isbn="978-1-4799-9988-0",
  url="https://www.fit.vut.cz/research/publication/11146/"
}
Files
Projects
Centrum excelence IT4Innovations, MŠMT, Operační program Výzkum a vývoj pro inovace, ED1.1.00/02.0070, start: 2011-01-01, end: 2015-12-31, completed
IARPA Building Speech Recognition for Keyword Search in a New Language in a Week with Limited Training Data (BABEL) - Babelon, BBN, start: 2012-03-05, end: 2016-11-04, completed
Meeting Assistant (MINT), TAČR, Program aplikovaného výzkumu a experimentálního vývoje ALFA, TA04011311, start: 2014-10-01, end: 2017-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top