Publication detail

Phonotactic Language Identification using High Quality Phoneme Recognition

MATĚJKA, P., SCHWARZ, P., ČERNOCKÝ, J., CHYTIL, P.

Original Title

Phonotactic Language Identification using High Quality Phoneme Recognition

Type

conference paper

Language

English

Original Abstract

Phoneme Recognizers followed by Language Modeling (PRLM) have
consistently yielded top performance in language identification
(LID) task. Parallel ordering of PRLMs (PPRLM) improves
performance even more.
Since tokenizer is the most important part of
LID system the high quality phoneme recognizer is employed. Two
different multilingual databases for training phoneme recognizers are
compared and the amount of sufficient training data is studied.
Reported results are on data from NIST
2003 LID evaluation. Our four PRLM systems have Equal Error Rate
(EER) of 2.4\% on 12 languages task. This result compares
favorably to the best known result from this task.

Keywords

Language identificaion, phoneme recognition

Authors

MATĚJKA, P., SCHWARZ, P., ČERNOCKÝ, J., CHYTIL, P.

RIV year

2005

Released

9. 9. 2005

Publisher

International Speech Communication Association

Location

Lisbon

ISBN

1018-4074

Periodical

European Conference EUROSPEECH

Year of study

2005

Number

9

State

Swiss Confederation

Pages from

2237

Pages to

2240

Pages count

4

URL

http://www.fit.vutbr.cz/~matejkap/publi/2005/eurospeech2005.pdf

BibTex

@inproceedings{BUT21478,
  author="Pavel {Matějka} and Petr {Schwarz} and Jan {Černocký} and Pavel {Chytil}",
  title="Phonotactic Language Identification using High Quality Phoneme Recognition",
  booktitle="Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology",
  year="2005",
  journal="European Conference EUROSPEECH",
  volume="2005",
  number="9",
  pages="2237--2240",
  publisher="International Speech Communication Association",
  address="Lisbon",
  issn="1018-4074",
  url="http://www.fit.vutbr.cz/~matejkap/publi/2005/eurospeech2005.pdf"
}