MANUAL AND SEMI-AUTOMATIC APPROACHES TO BUILDING A MULTILINGUAL PHONEME SET

被引：0
|
作者：
Egorova, Ekaterina [1 ]
Vesely, Karel [2 ]
Karafiat, Martin [2 ]
Janda, Milos [2 ]
Cernocky, Jan [2 ]
机构：
[1] Brno Univ Technol, BUT Speech FIT, CS-61090 Brno, Czech Republic
[2] Brno Univ Technol, IT4I Ctr Excellence, CS-61090 Brno, Czech Republic
来源：
2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2013年
关键词：
multilingual speech recognition; phoneme set mapping; phoneme confusion matrix; ADAPTATION;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
The paper addresses manual and semi-automatic approaches to building a multilingual phoneme set for automatic speech recognition. The first approach involves mapping and reduction of the phoneme set based on IPA and expert knowledge, the later one involves phoneme confusion matrix generated by a neural network. The comparison is done for 8 languages selected from GlobalPhone on three scenarios: 1) multilingual system with abundant data for all the languages, 2) multilingual systems excluding target language 3) multilingual systems with small amount of data for target languages. For 3), the multilingual system brought improvement for languages close enough to the others in the set.
引用
收藏
页码：7324 / 7328
页数：5
相关论文
共 50 条
  • [1] Semi-Automatic Building and Learning of a Multilingual Ontology
    Ben Mesmia, Fatma
    Mouhoub, Malek
    [J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (11)
  • [2] A New Approach for Semi-Automatic Building and Extending a Multilingual Terminology Thesaurus
    Horak, Ales
    Baisa, Vit
    Rambousek, Adam
    Suchomel, Vit
    [J]. INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2019, 28 (02)
  • [3] MANUAL ELLIPSOMETRY MADE SEMI-AUTOMATIC
    MELMED, AJ
    CARROLL, JJ
    [J]. REVIEW OF SCIENTIFIC INSTRUMENTS, 1978, 49 (09): : 1357 - 1358
  • [4] Semi-automatic indexing of documents with a multilingual thesaurus
    Schiel, U
    de Sousa, LMSF
    [J]. RIDE - MLIM 2003: THIRTEENTH INTERNATIONAL WORK SHOP ON RESEARCH ISSUES IN DATA ENGINEERING: MULTI-LINGUAL INFORMATION MANAGEMENT, PROCEEDINGS, 2003, : 31 - 38
  • [5] Semi-Automatic Alignment of Multilingual Parts of Speech Tagsets
    Yashothara, S.
    Uthayasanker, R. T.
    Dias, G., V
    Jayasena, S.
    [J]. COMPUTACION Y SISTEMAS, 2022, 26 (03): : 1365 - 1375
  • [6] An evaluation of manual and semi-automatic laughter annotation
    Ludusan, Bogdan
    Wagner, Petra
    [J]. INTERSPEECH 2020, 2020, : 621 - 625
  • [7] An interactive tool for manual, semi-automatic and automatic video annotation
    Bianco, Simone
    Ciocca, Gianluigi
    Napoletano, Paolo
    Schettini, Raimondo
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2015, 131 : 88 - 99
  • [8] Automatic, semi-automatic and manual validation of urban drainage data
    Branisavljevic, N.
    Prodanovic, D.
    Pavlovic, D.
    [J]. WATER SCIENCE AND TECHNOLOGY, 2010, 62 (05) : 1013 - 1021
  • [9] FLINTHAM,E - MANUAL SEMI-AUTOMATIC AND AUTOMATIC ARC WELDING
    JACKSON, E
    [J]. BRITISH WELDING JOURNAL, 1967, 14 (06): : 351 - &
  • [10] Semi-automatic generation of multilingual datasets for stance detection in Twitter
    Zotova, Elena
    Agerri, Rodrigo
    Rigau, German
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2021, 170
12345