APPLYING CONDITIONAL RANDOM FIELDS ON CHINESE SYLLABLE RECOGNITION

被引：0
|
作者：
Li, Jie [1 ]
Wang, Xuan [1 ]
Yang, Yi [1 ]
机构：
[1] Shenzhen Gradual Sch, Harbin Inst Technol, Intelligent Computat Res Ctr, Shenzhen, Peoples R China
来源：
2009 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2009), VOLS 1-9 | 2009年
关键词：
Chinese syllable recognition; CRFs; HMM;
D O I：
10.1109/ICSMC.2009.5346340
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Hidden Markov model (HMM) is successfully used in speech recognition. However, there is an unavoidable flaw in assuming strong independence for sequences labeling in HMM. While Conditional Random Fields (CRFs) can relax this assumption for HMM, and can also solve the label bias problem efficiently. In this paper, we investigate CRFs for Chinese syllable recognition in continuous speech due to its advantages. The experiments show that the syllable label CRF is able to achieve performance comparable to phone-based HMM.
引用
收藏
页码：1573 / 1577
页数：5
相关论文
共 50 条
  • [1] Applying conditional random fields to chinese shallow parsing
    Tan, YM
    Yao, TS
    Chen, Q
    Zhu, JB
    [J]. COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING, 2005, 3406 : 167 - 176
  • [2] Automatic recognition of Chinese organization name based on conditional random fields
    Zhang, Suxiang
    Zhang, Suxian
    Wang, Xiaojie
    [J]. PROCEEDINGS OF THE 2007 IEEE INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING AND KNOWLEDGE ENGINEERING (NLP-KE'07), 2007, : 229 - +
  • [3] Name Origin Recognition in Chinese Texts Based on Conditional Random Fields
    Zhang, Jing
    Xu, Jian
    Zhang, Yujie
    [J]. PROCEEDINGS OF 2013 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND COMPUTER APPLICATIONS (ICSA 2013), 2013, 92 : 129 - 134
  • [4] Chinese Unknown Word Recognition using improved Conditional Random Fields
    Xu, Yisu
    Wang, Xuan
    Tang, Buzhou
    Wang, Xiaolong
    [J]. ISDA 2008: EIGHTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, VOL 2, PROCEEDINGS, 2008, : 363 - 367
  • [5] Chinese Named Entity Recognition Based on Cascaded Conditional Random Fields
    Tan, Weixuan
    Kong, Fang
    Ni, Ji
    Zhou, Guodong
    [J]. 11TH CHINESE LEXICAL SEMANTICS WORKSHOP (CKSW2010), 2010, : 465 - 471
  • [6] Based Cascaded Conditional Random Fields Model for Chinese Named Entity Recognition
    Zhang Suxiang
    [J]. ICSP: 2008 9TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-5, PROCEEDINGS, 2008, : 1574 - 1578
  • [7] Hidden Conditional Random Fields for Phone Recognition
    Sung, Yun-Hsuan
    Jurafsky, Dan
    [J]. 2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 107 - 112
  • [8] Hidden Conditional Random Fields for Face Recognition
    Yang, Huachun
    [J]. 2013 INTERNATIONAL CONFERENCE ON COMPUTER SCIENCES AND APPLICATIONS (CSA), 2013, : 337 - 340
  • [9] Hidden Conditional Random Fields for Gait Recognition
    Hagui, Mabrouka
    Mahjoub, Mohamed Ali
    [J]. 2016 SECOND INTERNATIONAL IMAGE PROCESSING, APPLICATIONS AND SYSTEMS (IPAS), 2016,
  • [10] CRANDEM: Conditional Random Fields for Word Recognition
    Morris, Jeremy
    Fosler-Lussier, Eric
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 3035 - 3038
12345