Publication detail

Improving Language Models for ASR Using Translated In-domain Data

KOMBRINK, S. MIKOLOV, T. KARAFIÁT, M. BURGET, L.

Original Title

Improving Language Models for ASR Using Translated In-domain Data

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

This paper descibes how to do the acquisition of in-domain training data for the puspose of building speech recognition systems for under-resourced languages.

Keywords

Low Resource ASR, Language Modeling, Machine Translation

Authors

KOMBRINK, S.; MIKOLOV, T.; KARAFIÁT, M.; BURGET, L.

RIV year

2012

Released

25. 3. 2012

Publisher

IEEE Signal Processing Society

Location

Kyoto

ISBN

978-1-4673-0044-5

Book

Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing

Pages from

4405

Pages to

4408

Pages count

4

URL

BibTex

@inproceedings{BUT91478,
  author="Stefan {Kombrink} and Tomáš {Mikolov} and Martin {Karafiát} and Lukáš {Burget}",
  title="Improving Language Models for ASR Using Translated In-domain Data",
  booktitle="Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing",
  year="2012",
  pages="4405--4408",
  publisher="IEEE Signal Processing Society",
  address="Kyoto",
  doi="10.1109/ICASSP.2012.6288896",
  isbn="978-1-4673-0044-5",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2012/kombrink_icassp2012_0004405.pdf"
}