Skip to content

Detail of publication

Citation

Pražák, A. and Psutka, J. and Hoidekr, J. and Kanis, J. and Müller, L. and Psutka, J. : Adaptive language model in automatic online subtitling . Proceedings of the second IASTED international conference on Computational intelligence, p. 479-483, ACTA Press, Anaheim, 2006.

Abstract

This paper describes an adaptive language model for recognition tasks, where person names are specific for each recognition session and have to be added to the recognition vocabulary. Creation of an adaptive language model with word (name) classes is illustrated on two different tasks of automatic online subtitling: subtitling of parliament meetings (1.5 % of names) and ice-hockey matches (15 % of names). The second part outlines the system for automatic online subtitling with vocabulary up to 100 000 words in real-time. The recognition system is based on Hidden Markov Models, lexical trees and bigram language model. Finally, experimental results with and without the adaptive language model are reported and discussed.

Detail of publication

Title: Adaptive language model in automatic online subtitling
Author: Pražák, A. ; Psutka, J. ; Hoidekr, J. ; Kanis, J. ; Müller, L. ; Psutka, J.
Language: English
Date of publication: 20 Nov 2006
Year: 2006
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Proceedings of the second IASTED international conference on Computational intelligence
Page: 479 - 483
ISBN: 0-88986-602-3
Publisher: ACTA Press
Address: Anaheim
Date: 20 Nov 2006 - 22 Nov 2006
/ 2008-04-03 16:06:12 /

Keywords

LVCSR, real-time recognition, class-based language model, automatic subtitling

BibTeX

@INPROCEEDINGS{PrazakA_2006_Adaptivelanguage,
 author = {Pra\v{z}\'{a}k, A. and Psutka, J. and Hoidekr, J. and Kanis, J. and M\"{u}ller, L. and Psutka, J.},
 title = {Adaptive language model in automatic online subtitling},
 year = {2006},
 publisher = {ACTA Press},
 journal = {Proceedings of the second IASTED international conference on Computational intelligence},
 address = {Anaheim},
 pages = {479-483},
 ISBN = {0-88986-602-3},
 url = {http://www.kky.zcu.cz/en/publications/PrazakA_2006_Adaptivelanguage},
}