Detail publikace

Phoneme Recognition Tuning for Language Identification System

Pavel Matejka

Originální název

Phoneme Recognition Tuning for Language Identification System

Anglický název

Phoneme Recognition Tuning for Language Identification System

Jazyk

en

Originální abstrakt

This paper provides brief description of Language Identification (LID) system based on phoneme recognizer followed by language models (PRLM). Tuning phoneme recognizers for this task can increase performance of the whole system. Reported results are on data from NIST 2003 LID evaluation. Our system has Equal Error Rate (EER) 5.4\% on task with 12 languages. This result compares favorably to the best known Parallel PRLM results from this evaluation.

Anglický abstrakt

This paper provides brief description of Language Identification (LID) system based on phoneme recognizer followed by language models (PRLM). Tuning phoneme recognizers for this task can increase performance of the whole system. Reported results are on data from NIST 2003 LID evaluation. Our system has Equal Error Rate (EER) 5.4\% on task with 12 languages. This result compares favorably to the best known Parallel PRLM results from this evaluation.

Dokumenty

BibTex


@inproceedings{BUT14355,
  author="Pavel {Matějka}",
  title="Phoneme Recognition Tuning for Language Identification System",
  annote="This paper provides brief description of Language Identification (LID) system based on phoneme recognizer followed by language models (PRLM). Tuning phoneme recognizers for this task can increase performance of the whole system. Reported results are on data from NIST 2003 LID evaluation. Our system has Equal Error Rate (EER) 5.4\% on task
with 12 languages. This result compares favorably to the best known Parallel PRLM results from this evaluation.",
  address="FEEC BUT",
  booktitle="Proceedings of the 11th conference STUDENT EEICT 2005",
  chapter="14355",
  institution="FEEC BUT",
  year="2005",
  month="april",
  pages="658",
  publisher="FEEC BUT",
  type="conference paper"
}