Graphical models for integrating syllabic information

被引:4
|
作者
Bartels, Chris D. [1 ]
Bilmes, Jeff A. [1 ]
机构
[1] Univ Washington, Dept Elect Engn, Seattle, WA 98195 USA
来源
COMPUTER SPEECH AND LANGUAGE | 2010年 / 24卷 / 04期
关键词
Speech recognition; Graphical models; Dynamic Bayesian networks; Syllables; SPEECH;
D O I
10.1016/j.csl.2009.11.001
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present graphical model based methodology that enhances a speech recognizer with information about syllabic segmentations. The segmentations are specified by locations of syllable nuclei, and the graphical models are able to consider these locations as "soft" information. The graphs give improved discrimination between speech and noise when compared to a baseline model. When using locations derived from oracle information an overall improvement is shown, and when the oracle syllable nuclei are augmented with information about lexical stress the methods give additional improvements over locations alone. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:685 / 697
页数:13
相关论文
共 50 条
  • [1] Integrating approximate single factor graphical models
    Fan, Xinyan
    Fang, Kuangnan
    Ma, Shuangge
    Zhang, Qingzhao
    STATISTICS IN MEDICINE, 2020, 39 (02) : 146 - 155
  • [2] Integrating additional knowledge into the estimation of graphical models
    Bu, Yunqi
    Lederer, Johannes
    INTERNATIONAL JOURNAL OF BIOSTATISTICS, 2022, 18 (01): : 1 - 17
  • [3] Optimal Value of Information in Graphical Models
    Krause, Andreas
    Guestrin, Carlos
    JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2009, 35 : 557 - 591
  • [4] A focused information criterion for graphical models
    Eugen Pircalabelu
    Gerda Claeskens
    Lourens Waldorp
    Statistics and Computing, 2015, 25 : 1071 - 1092
  • [5] A focused information criterion for graphical models
    Pircalabelu, Eugen
    Claeskens, Gerda
    Waldorp, Lourens
    STATISTICS AND COMPUTING, 2015, 25 (06) : 1071 - 1092
  • [6] Processing syllabic and sub-syllabic information in Cantonese
    Chen, HC
    Yip, MCW
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2000, 35 (3-4) : 42 - 42
  • [7] Enhancing graphical information system models with VRML
    Huotari, J
    Niemelä, M
    SIXTH INTERNATIONAL CONFERENCE ON INFORMATION VISUALISATION, PROCEEDINGS, 2002, : 670 - 676
  • [8] Collaborative Multi Organ Segmentation by Integrating Deformable and Graphical Models
    Uzunbas, Mustafa Goekhan
    Chen, Chao
    Zhang, Shaoting
    Pohl, Kilian M.
    Li, Kang
    Metaxas, Dimitris
    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2013, PT II, 2013, 8150 : 157 - 164
  • [9] Constructing Graphical Models via the Focused Information Criterion
    Claeskens, Gerda
    Pircalabelu, Eugen
    Waldorp, Lourens
    MODELING AND STOCHASTIC LEARNING FOR FORECASTING IN HIGH DIMENSIONS, 2015, 217 : 55 - 78
  • [10] Introduction to the special issue on Graphical Models and Information Retrieval
    Fernandez-Luna, Juan M.
    Huete, Juan F.
    Piwowarski, Benjamin
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2009, 50 (07) : 929 - 931