Comparing word, character, and phoneme n-grams for subjective utterance recognition

被引：0
|
作者：
Wilson, Theresa [1 ]
Raaijmakers, Stephan [2 ]
机构：
[1] Univ Edinburgh, Sch Informat, Edinburgh, Midlothian, Scotland
[2] TNO Informat & Commun Technol, Delft, Netherlands
来源：
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | 2008年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we compare the performance of classifiers trained using word n-grams, character n-grams, and phoneme n-grams for recognizing subjective utterances in multiparty conversation. We show that there is value in using very shallow linguistic representations, such as character n-grams, for recognizing subjective utterances, in particular, gains in the recall of subjective utterances.
引用
收藏
页码：1614 / +
页数：2
相关论文
共 50 条
  • [1] The subjective frequency of word n-grams
    Shaoul, Cyrus
    Westbury, Chris F.
    Baayen, R. Harald
    [J]. PSIHOLOGIJA, 2013, 46 (04) : 497 - 537
  • [2] SPEECH RECOGNITION USING FUNCTION-WORD N-GRAMS AND CONTENT-WORD N-GRAMS
    ISOTANI, R
    MATSUNAGA, S
    SAGAYAMA, S
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1995, E78D (06) : 692 - 697
  • [3] Which Granularity to Bootstrap a Multilingual Method of Document Alignment: Character N-grams or Word N-grams?
    Lecluze, Charlotte
    Rigouste, Lois
    Giguet, Emmanuel
    Lucas, Nadine
    [J]. CORPUS RESOURCES FOR DESCRIPTIVE AND APPLIED STUDIES. CURRENT CHALLENGES AND FUTURE DIRECTIONS: SELECTED PAPERS FROM THE 5TH INTERNATIONAL CONFERENCE ON CORPUS LINGUISTICS (CILC2013), 2013, 95 : 473 - 481
  • [4] Combining Word and Character N-grams for Detecting Deceptive Opinions
    Siagian, Al Hafiz Akbar Maulana
    Aritsugi, Masayoshi
    [J]. 2017 IEEE 41ST ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 1, 2017, : 828 - 833
  • [5] IDF for Word N-grams
    Shirakawa, Masumi
    Hara, Takahiro
    Nishio, Shojiro
    [J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2017, 36 (01)
  • [6] A comparison of character n-grams and dictionaries used for script recognition
    Brakensiek, A
    Rigoll, G
    [J]. SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 241 - 245
  • [7] Word-conditioned phone N-grams for speaker recognition
    Lei, Howard
    Mirghafori, Nikki
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 253 - +
  • [8] Unconstrained Offline Handwriting Recognition using Connectionist Character N-grams
    Zamora-Martinez, F.
    Castro-Bleda, M. J.
    Espana-Boquera, S.
    Gorbe-Moya, J.
    [J]. 2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [9] Measuring similarity between Karel programs using character and word n-grams
    G. Sidorov
    M. Ibarra Romero
    I. Markov
    R. Guzman-Cabrera
    L. Chanona-Hernández
    F. Velásquez
    [J]. Programming and Computer Software, 2017, 43 : 47 - 50
  • [10] Variable word rate n-grams
    Gotoh, Y
    Renals, S
    [J]. 2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 1591 - 1594
12345