Skip to content

Publications

Detail of publication

Citation

Pražák, A. and Ircing, P. and Müller, L. : Language Model Adaptation Using Different Class-Based Models . SPECOM 2007 Proceedings, p. 449-454, Moscow State Linguistic University, Moscow, 2007.

Download PDF

PDF

Abstract

The paper presents two different methods for adding previously unseen words into the LVCSR system. Both methods employ the principles of class-based language modeling – the first one exploits task-specific knowledge, the second one is fully automatic and task independent. Extensive test of the proposed language models in the real-time ASR system showed that both techniques provide a consistent improvement in terms of recognition accuracy. Moreover, the contributions from both methods appear to be additive, yielding a total improvement of up to 2 % absolute.

Detail of publication

Title: Language Model Adaptation Using Different Class-Based Models
Author: Pražák, A. ; Ircing, P. ; Müller, L.
Language: English
Date of publication: 15 Oct 2007
Year: 2007
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: SPECOM 2007 Proceedings
Page: 449 - 454
ISBN: 6-7452-0110-x
Publisher: Moscow State Linguistic University
Address: Moscow
Date: 15 Oct 2007 - 18 Oct 2007
/ 2008-10-17 14:15:32 /

Keywords

ASR, LVCSR, HMM, real-time, class-based language model, morphological tag

BibTeX

@INPROCEEDINGS{PrazakA_2007_LanguageModel,
 author = {Pra\v{z}\'{a}k, A. and Ircing, P. and M\"{u}ller, L.},
 title = {Language Model Adaptation Using Different Class-Based Models},
 year = {2007},
 publisher = {Moscow State Linguistic University},
 journal = {SPECOM 2007 Proceedings},
 address = {Moscow},
 pages = {449-454},
 ISBN = {6-7452-0110-x},
 url = {http://www.kky.zcu.cz/en/publications/PrazakA_2007_LanguageModel},
}