An Equalized Heteroscedastic Linear Discriminant Analysis Algorithm

被引：2
|
作者：
Zhang, Wei-Qiang [1 ]
Liu, Jia [1 ]
机构：
[1] Tsinghua Univ, Dept Elect Engn, Tsinghua Natl Lab Informat Sci & Technol, Beijing 100084, Peoples R China
来源：
IEEE SIGNAL PROCESSING LETTERS | 2008年 / 15卷
基金：
中国国家自然科学基金;
关键词：
Equalization; feature extraction; heteroscedastic linear discriminant analysis (HLDA);
D O I：
10.1109/LSP.2008.2001561
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Heteroscedastic linear discriminant analysis (HLDA) is a widely used feature extraction algorithm. This method, however, suffers from unbalanced training data in some cases. In this letter, we equalize the objective function and statistics of HLDA and present an equalized HLDA algorithm, which balances the training data according to the class prior probability. Simulations as well as experimental results for the task of language identification are used to demonstrate the effectiveness of the proposed method.
引用
收藏
页码：585 / 588
页数：4
相关论文
共 50 条
  • [1] Improve Heteroscedastic Discriminant Analysis by Using CBP Algorithm
    Alzubi, Jafar A.
    Yaghoubi, Ali
    Gheisari, Mehdi
    Qin, Yongrui
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2018, PT II, 2018, 11335 : 130 - 144
  • [2] Integration of heteroscedastic linear discriminant analysis (HLDA) into adaptive training
    Stemmer, Georg
    Brugnara, Fabio
    2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13, 2006, : 1185 - 1188
  • [3] A Semi-supervised Version of Heteroscedastic Linear Discriminant Analysis
    Zhou, Haolang
    Karakos, Damianos
    Andreou, Andreas G.
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 868 - 871
  • [4] Heteroscedastic Probabilistic Linear Discriminant Analysis with Semi-supervised Extension
    Zhang, Yu
    Yeung, Dit-Yan
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, PT II, 2009, 5782 : 602 - +
  • [5] Improve handwritten character recognition performance by heteroscedastic linear discriminant analysis
    Liu, Hailong
    Ding, Xiaoqing
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 880 - +
  • [6] Minimum phoneme error based heteroscedastic linear discriminant analysis for speech recognition
    Zhang, B
    Matsoukas, S
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 925 - 928
  • [7] Time-Frequency Cepstral Features and Heteroscedastic Linear Discriminant Analysis for Language Recognition
    Zhang, Wei-Qiang
    He, Liang
    Deng, Yan
    Liu, Jia
    Johnson, Michael T.
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (02): : 266 - 276
  • [8] Two-Dimensional Heteroscedastic Linear Discriminant Analysis for age-group classification
    Ueki, Kazuya
    Hayashida, Teruhide
    Kobayashi, Tetsunori
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2006, : 585 - +
  • [9] Robust heteroscedastic linear discriminant analysis and LCRC posterior features in meeting data recognition
    Karafiat, Martin
    Grezl, Frantisek
    Schwarz, Petr
    Burget, Lukas
    Cernocky, Jan
    MACHINE LEARNING FOR MULTIMODAL INTERACTION, 2006, 4299 : 275 - +
  • [10] Fast algorithm for online linear discriminant analysis
    Hiraoka, K
    Hamahira, M
    Hidai, K
    Mizoguchi, H
    Mishima, T
    Yoshizawa, S
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2001, E84A (06) : 1431 - 1441
12345