The Variational EM algorithm for on-line identification of extended AR models

被引：0
|
作者：
Smídl, V [1 ]
Quinn, A [1 ]
机构：
[1] Acad Sci Czech Republic, UTIA, Prague, Czech Republic
来源：
2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING | 2005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：
The AutoRegressive (AR) model is extended to cope with a wide class of possible transformations and degradations. The Variational Bayes (VB) procedure is used to restore conjugacy. The resulting Bayesian recursive identification procedure has many of the desirable computational properties of the classical RLS procedure. During each time-step, an iterative Variational EM (VEM) procedure is required to obtain the necessary moments. The procedure is used to reconstruct an outlier-corrupted AR process and a noisy speech segment. The VB scheme appears to offer improved performance over the related Quasi-Bayes (QB) scheme in the case of time-variant component weights.
引用
收藏
页码：117 / 120
页数：4
相关论文
共 50 条
  • [41] On-line Inertia Identification Algorithm for PI Parameters Optimization in Speed Loop
    Niu, Li
    Xu, Dianguo
    Yang, Ming
    Gui, Xianguo
    Liu, Zijian
    IEEE TRANSACTIONS ON POWER ELECTRONICS, 2015, 30 (02) : 849 - 859
  • [42] Better on-line identification algorithm with impairment of aircraft control surfaces considered
    Zhu, Qi
    Ye, Fang
    Liu, Jun-Lei
    Feng, Guang-Zeng
    Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University, 2005, 23 (03): : 316 - 320
  • [43] Robust bootstrapping algorithm of speaker models for on-line unsupervised speaker indexing
    School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China
    Ruan Jian Xue Bao, 2007, 3 (608-616):
  • [44] On-line identification of induction motors using discrete models for sinusoidal signals
    do Prado, Alcindo, Jr.
    de Sousa, Antonio Heronaldo
    Ferrari, Sandro Mauro
    IECON 2006 - 32ND ANNUAL CONFERENCE ON IEEE INDUSTRIAL ELECTRONICS, VOLS 1-11, 2006, : 1578 - +
  • [45] On-line clustering method for Takagi-Sugeno fuzzy models identification
    Martínez, Boris
    Herrera, Francisco
    Fernández, Jesús
    Marichal, Erick
    RIAI - Revista Iberoamericana de Automatica e Informatica Industrial, 2008, 5 (03): : 63 - 69
  • [46] On-line identification method for models of platform seeker disturbance rejection rate
    Xiao, Bowen
    Ma, Zeyuan
    Lu, Tianyu
    Xia, Qunli
    Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2024, 46 (11): : 3595 - 3604
  • [47] On-line identification of MIMO evolving Takagi-Sugeno fuzzy models
    Angelov, P
    Xydeas, C
    Filev, D
    2004 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, PROCEEDINGS, 2004, : 55 - 60
  • [48] Optimized feedforward neural networks. for on-line identification of nonlinear models
    Alessandri, A
    Sanguineti, M
    Maggiore, M
    PROCEEDINGS OF THE 41ST IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 2002, : 1751 - 1756
  • [49] On-line identification of induction motors through discrete models for sinusoidal signals
    do Prado, Alcindo, Jr.
    de Sousa, Antonio H.
    Ferrari, Sandro M.
    2006 INTERNATIONAL SYMPOSIUM ON POWER ELECTRONICS, ELECTRICAL DRIVES, AUTOMATION AND MOTION, VOLS 1-3, 2006, : 1287 - +
  • [50] On-line clustering method for Takagi-Sugeno fuzzy models identification
    Martinez, Boris
    Herrera, Francisco
    Fernandez, Jesils
    Marichal, Erick
    REVISTA IBEROAMERICANA DE AUTOMATICA E INFORMATICA INDUSTRIAL, 2008, 5 (03): : 63 - +
12345