Publication Details

BUT OpenSAT 2017 speech recognition system

KARAFIÁT, M.; BASKAR, M.; SZŐKE, I.; MALENOVSKÝ, V.; VESELÝ, K.; GRÉZL, F.; BURGET, L.; ČERNOCKÝ, J. BUT OpenSAT 2017 speech recognition system. In Proceedings of Interspeech 2018. Proceedings of Interspeech. Hyderabad: International Speech Communication Association, 2018. p. 2638-2642. ISSN: 1990-9772.
Czech title
VUT systém rozpoznávání řeči pro OpenSAT 2017
Type
conference paper
Language
English
Authors
URL
Keywords

speech recognition, multilingual training, BLSTM, data augmentation, robustness

Abstract

(ASR) systems for two domains in OpenSAT evaluations: LowResourced Languages and Public Safety Communications. Thefirst was challenging due to lack of training data, therefore multilingualapproaches for BLSTM training were employed andrecently published Residual Memory Networks requiring lesstraining data were used. Combination of both approaches led tosuperior performance. The second domain was challenging dueto recording in extreme conditions: specific channel, speakerunder stress, high levels of noise. A data augmentation processwas very important to get reasonably good performance.

Published
2018
Pages
2638–2642
Journal
Proceedings of Interspeech, vol. 2018, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2018
Conference
Interspeech Conference, Hyderabad, India, IN
Publisher
International Speech Communication Association
Place
Hyderabad
DOI
UT WoS
000465363900553
EID Scopus
BibTeX
@inproceedings{BUT155099,
  author="Martin {Karafiát} and Murali Karthick {Baskar} and Igor {Szőke} and Vladimír {Malenovský} and Karel {Veselý} and František {Grézl} and Lukáš {Burget} and Jan {Černocký}",
  title="BUT OpenSAT 2017 speech recognition system",
  booktitle="Proceedings of Interspeech 2018",
  year="2018",
  journal="Proceedings of Interspeech",
  volume="2018",
  number="9",
  pages="2638--2642",
  publisher="International Speech Communication Association",
  address="Hyderabad",
  doi="10.21437/Interspeech.2018-2457",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/2457.html"
}
Files
Back to top