Phonotactic language identification using high quality phoneme recognition (2005)
| Citations: | 4 - 1 self |
BibTeX
@MISC{Matějka05phonotacticlanguage,
author = {Pavel Matějka and Petr Schwarz and Pavel Chytil},
title = {Phonotactic language identification using high quality phoneme recognition},
year = {2005}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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. 1.
Citations
| 79 | Comparison of four approaches to automatic language identification of telephone speech - Zissman - 1996 |
| 29 | Temporal patterns (TRAPS) in ASR of noisy speech - Hermansky, Sharma - 1999 |
| 24 | An approach to automatic language identification based on language-dependent phone recognition - Yan, Barnard |
| 16 | discriminative approaches to automatic language identification - Singer, Torres-Carrasquillo, et al. |
| 16 | Towards Lower Error Rates in Phoneme Recognition - Schwarz, Matejka, et al. - 2004 |
| 9 | Nist 2003 language recognition evaluation - Martin, Przybocki - 2003 |
| 6 | Recognition of Phoneme Strings using TRAP Technique - Schwarz, Matějka, et al. - 2003 |
| 2 | telephone speech of 15 different languages or dialects,” www.ldc.upenn.edu/Catalog/byType.jsp#speech.telephone - corpus |
| 1 | Tuning phonotactic language identificaion system - Matějka - 2005 |
