Language model adaptation in machine translation from speech

被引：0
|
作者：
Bulyko, Ivan [1 ]
Matsoukas, Spyros [1 ]
Schwartz, Richard [1 ]
Nguyen, Long [1 ]
Makhoul, John [1 ]
机构：
[1] BBN Technol, 10 Moulton St, Cambridge, MA 02138 USA
来源：
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3 | 2007年
关键词：
speech translation; language modeling; domain adaptation;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper investigates the use of several language model adaptation techniques applied to the task of machine translation from Arabic broadcast speech. Unsupervised and discriminative approaches slightly outperform the traditional perplexity-based optimization technique. Language model adaptation, when used for n-best rescoring, improves machine translation performance by 0.3-0.4 BLEU and reduces translation edit rate (TER) by 0.2-0.5% compared to an unadapted LM.
引用
收藏
页码：117 / +
页数：2
相关论文
共 50 条
  • [1] RESAMPLING AUXILIARY DATA FOR LANGUAGE MODEL ADAPTATION IN MACHINE TRANSLATION FOR SPEECH
    Maskey, Sameer
    Sethy, Abhinav
    [J]. 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 4817 - +
  • [2] Discriminative language model adaptation for Mandarin broadcast speech transcription and translation
    Liu, X. A.
    Byrne, W. J.
    Gales, M. J. F.
    de Gispert, A.
    Tomalin, M.
    Woodland, P. C.
    Yu, K.
    [J]. 2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 153 - 158
  • [3] Data Categorization and Model Weighting Approach for Language Model Adaptation in Statistical Machine Translation
    AbuHamad, Mohammed
    Mohd, Masnizah
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2019, 10 (01) : 135 - 141
  • [4] LANGUAGE MODEL BOOTSTRAPPING USING NEURAL MACHINE TRANSLATION FOR CONVERSATIONAL SPEECH RECOGNITION
    Punjabi, Surabhi
    Arsikere, Harish
    Garimella, Sri
    [J]. 2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), 2019, : 487 - 493
  • [5] Language Model Method for Collocation Rules of Parts of Speech in Machine Translation System
    Liu, Jinhui
    Zhang, Feng
    [J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2024, 23 (08) : 18 - 18
  • [6] Language Model Adaptation for a Speech to Sign Language Translation System using Web Frequencies and a MAP Framework
    Fernando D'Haro, Luis
    San-Segundo, Ruben
    de Cordoba, Ricardo
    Bungeroth, Jan
    Stein, Daniel
    Ney, Hermann
    [J]. INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 2199 - +
  • [7] INTEGRATING MACHINE TRANSLATION AND SPEECH SYNTHESIS COMPONENT FOR ENGLISH TO DRAVIDIAN LANGUAGE SPEECH TO SPEECH TRANSLATION SYSTEM
    Sangeetha, J.
    Jothilakshmi, S.
    [J]. JOURNAL OF ENGINEERING SCIENCE AND TECHNOLOGY, 2015, 10 (02): : 196 - 211
  • [8] NAME-AWARE LANGUAGE MODEL ADAPTATION AND SPARSE FEATURES FOR STATISTICAL MACHINE TRANSLATION
    Wang, Wen
    Li, Haibo
    Ji, Heng
    [J]. 2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2015, : 324 - 330
  • [9] ADAPTATION OF LECTURE SPEECH RECOGNITION SYSTEM WITH MACHINE TRANSLATION OUTPUT
    Ng, Raymond W. M.
    Hain, Thomas
    Cohn, Trevor
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 8401 - 8405
  • [10] Trends and challenges in language modeling for speech recognition and machine translation
    Schwenk, Holger
    [J]. 2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 23 - 23
12345