Publication Details

Czech Speech Recognizer for Multiple Environments

GLEMBEK Ondřej, KARAFIÁT Martin, BURGET Lukáš and ČERNOCKÝ Jan. Czech Speech Recognizer for Multiple Environments. In: Radioeletronika 2006. Bratislava, 2006, pp. 1-4.
Czech title
Rozpoznávač češtiny pro různá prostředí
Type
conference paper
Language
english
Authors
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

speech, recognition, automatic, artiffical inteligence, training, czech, database, acoustic, modelling, modeling, language

Abstract

This paper presents our work on building a largevocabulary continuous speech recognition (LVCSR) system for Czech, capable of op eration in multiple environments. SpeeCon and Temic speech databases were used to define a data-set for training acoustic models, attention was paid to unification of these two resources. The test set was also defined using these corp ora with careful choice of segments not overlapping with the training data. The system was completed by a language model trained on Czech National corpus. The recognition was performed using DUCoder an LVCSR stack decoder. Experimental results on the LVCSR task give a reference score of the system for future improvements.

Published
2006
Pages
1-4
Proceedings
Radioeletronika 2006
Conference
16th International Czech-Slovak Scientific conference Radioelektronika 2006, Bratislava, SK
Place
Bratislava, SK
BibTeX 
@INPROCEEDINGS{FITPUB8219,
   author = "Ond\v{r}ej Glembek and Martin Karafi\'{a}t and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Czech Speech Recognizer for Multiple Environments",
   pages = "1--4",
   booktitle = "Radioeletronika 2006",
   year = 2006,
   location = "Bratislava, SK",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8219"
}
Back to top