Result Details
Tuning Phonotactic Language Identificaion System
MATĚJKA, P.; SCHWARZ, P.; ČERNOCKÝ, J.; CHYTIL, P. Tuning Phonotactic Language Identificaion System. Brno: Faculty of Information Technology BUT, 2005. p. 1-5.
Type
report
Language
English
Authors
Matějka Pavel, Ing., Ph.D., DCGM (FIT), UREL (FEEC)
Schwarz Petr, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Chytil Pavel, Ing., Ph.D., UREL (FEEC)
Schwarz Petr, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Chytil Pavel, Ing., Ph.D., UREL (FEEC)
Abstract
This report 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 ofthe whole system. Reported results are on data from NIST 2003 LIDevaluation. Our system has Equal Error Rate (EER) 5.4% on task with 12languages. This result compares favorably to the best known ParallelPRLM results from this evaluation.
Keywords
Language identificaion, phoneme recognition
URL
Published
2005
Pages
1–5
Publisher
Faculty of Information Technology BUT
Place
Brno
BibTeX
@misc{BUT57580,
author="Pavel {Matějka} and Petr {Schwarz} and Jan {Černocký} and Pavel {Chytil}",
title="Tuning Phonotactic Language Identificaion System",
year="2005",
pages="1--5",
publisher="Faculty of Information Technology BUT",
address="Brno",
url="http://www.fit.vutbr.cz/~matejkap/publi/2005/TechRep_TuneLID.pdf"
}
Projects
New trends in research and application of voice technology, GACR, Standardní projekty, GA102/05/0278, start: 2005-01-01, end: 2007-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments