Publication detail

Zero-Cost Speech Recognition Task at Mediaeval 2016

SZŐKE, I. ANGUERA, X.

Original Title

Zero-Cost Speech Recognition Task at Mediaeval 2016

Type

conference paper

Language

English

Original Abstract

The main goal of the Zero-Cost Speech Recognition task is to bring researchers together on the topic of training ASR systems using only publicly available data. In particular, the task consists on the development of either an LVCSR or a subword speech recognizer on a given target language. For this year we selected Vietnamese as the target language The organizers provided participants several sets of pub- licly available data combined with one proprietary set gath- ered for this evaluation. Participants are free to find and use other publicly available resources (free for research pur- poses). These resources must be shared with other partici- pants till end of July. The data-set for the evaluation is then fixed and no outside data can be used.

Keywords

speech recognition, zero cost

Authors

SZŐKE, I.; ANGUERA, X.

Released

10. 10. 2016

Publisher

CEUR-WS.org

Location

Hilversum

ISBN

1613-0073

Periodical

CEUR Workshop Proceedings

Year of study

2016

Number

1739

State

Federal Republic of Germany

Pages from

1

Pages to

3

Pages count

3

URL

BibTex

@inproceedings{BUT163809,
  author="Igor {Szőke} and Xavier {Anguera}",
  title="Zero-Cost Speech Recognition Task at Mediaeval 2016",
  booktitle="CEUR Workshop Proceedings",
  year="2016",
  journal="CEUR Workshop Proceedings",
  volume="2016",
  number="1739",
  pages="1--3",
  publisher="CEUR-WS.org",
  address="Hilversum",
  issn="1613-0073",
  url="https://www.fit.vut.cz/research/publication/12269/"
}