Incremental language modeling for automatic transcription of broadcast news

被引：1
|
作者：
Ohtsuki, Katsutoshi [1 ]
Nguyen, Long
机构：
[1] NTT Corp, Cyber Space Labs, Yokosuka, Kanagawa 2390847, Japan
[2] BBN Syst & Technol Corp, Cambridge, MA 02138 USA
来源：
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2007年 / E90D卷 / 02期
关键词：
speech recognition; out-of-vocabulary; language model; broadcast news;
D O I：
10.1093/ietisy/e90-d.2.526
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, we address the task of incremental language modeling for automatic transcription of broadcast news speech. Daily broadcast news naturally contains new words that are not in the lexicon of the speech recognition system but are important for downstream applications such as information retrieval or machine translation. To recognize those new words, the lexicon and the language model of the speech recognition system need to be updated periodically. We propose a method of estimating a list of words to be added to the lexicon based on some time-series text data. The experimental results on the RT04 Broadcast News data and other TV audio data showed that this method provided an impressive and stable reduction in both out-of-vocabulary rates and speech recognition word error rates.
引用
收藏
页码：526 / 532
页数：7
相关论文
共 50 条
  • [1] Language Modeling for Automatic Turkish Broadcast News Transcription
    Arisoy, Ebru
    Sak, Hasim
    Saraclar, Murat
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2748 - 2751
  • [2] Incremental language modeling for broadcast news
    Ohtsuki, K
    Nguyen, L
    [J]. 2005 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2005, : 139 - 144
  • [3] Improved modeling and efficiency for automatic transcription of Broadcast News
    Sankar, A
    Gadde, VRR
    Stolcke, A
    Weng, FL
    [J]. SPEECH COMMUNICATION, 2002, 37 (1-2) : 133 - 158
  • [4] Automatic transcription of Broadcast News
    Chen, SS
    Eide, E
    Gales, MJF
    Gopinath, RA
    Kanvesky, D
    Olsen, P
    [J]. SPEECH COMMUNICATION, 2002, 37 (1-2) : 69 - 87
  • [5] Automatic transcription of Broadcast News data
    Pallett, DS
    Lamel, L
    [J]. SPEECH COMMUNICATION, 2002, 37 (1-2) : 1 - 2
  • [6] Automatic language identification in broadcast news
    Backfried, G
    Rainoldi, R
    Riedler, J
    [J]. PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1406 - 1410
  • [7] Unsupervised stemmed text corpus for language modeling and transcription of Telugu broadcast news
    Mythilisharan Pala
    Laxminarayana Parayitam
    Venkataramana Appala
    [J]. International Journal of Speech Technology, 2020, 23 : 695 - 704
  • [8] Unsupervised stemmed text corpus for language modeling and transcription of Telugu broadcast news
    Pala, Mythilisharan
    Parayitam, Laxminarayana
    Appala, Venkataramana
    [J]. INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2020, 23 (03) : 695 - 704
  • [9] On-line incremental speaker adaptation for broadcast news transcription
    Zhang, ZP
    Furui, S
    Ohtsuki, K
    [J]. SPEECH COMMUNICATION, 2002, 37 (3-4) : 271 - 281
  • [10] Unsupervised vocabulary expansion for automatic transcription of broadcast news
    Ohtsuki, K
    Hiroshima, N
    Oku, M
    Imamura, A
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 1021 - 1024
12345