Application of the variance compensation likelihood measure for robust hidden Markov model in noise

Kuo Chang Huang; Shin Lun Tung; Yau Tarng Juang

doi:10.1016/S0167-8655(00)00134-3

Application of the variance compensation likelihood measure for robust hidden Markov model in noise

Kuo Chang Huang, Shin Lun Tung, Yau Tarng Juang

Department of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

This letter presents covariance matrix adaptation based upon the incorporation of the projection-based group delay scheme (PGDS) with a semi-continuous hidden Markov model (HMM) for the minimization of undesirable effects in noisy environments. The proposed approach fits the covariance matrix using a variance adaptive function to balance the mismatch between different environments.

Original language	English
Pages (from-to)	353-358
Number of pages	6
Journal	Pattern Recognition Letters
Volume	22
Issue number	3-4
DOIs	https://doi.org/10.1016/S0167-8655(00)00134-3
State	Published - Mar 2001

Keywords

Group delay scheme
Hidden Markov model
Mean compensation bias
Projection measure
Variance adaptive fuction

Access to Document

10.1016/S0167-8655(00)00134-3

Cite this

@article{ebfa411f30374ad8a482b5e25993a792,

title = "Application of the variance compensation likelihood measure for robust hidden Markov model in noise",

abstract = "This letter presents covariance matrix adaptation based upon the incorporation of the projection-based group delay scheme (PGDS) with a semi-continuous hidden Markov model (HMM) for the minimization of undesirable effects in noisy environments. The proposed approach fits the covariance matrix using a variance adaptive function to balance the mismatch between different environments.",

keywords = "Group delay scheme, Hidden Markov model, Mean compensation bias, Projection measure, Variance adaptive fuction",

author = "Huang, {Kuo Chang} and Tung, {Shin Lun} and Juang, {Yau Tarng}",

note = "Funding Information: This work was partially supported by the National Science Council of the Republic of China under the contract no. NSC88-2213-E-008-024. ",

year = "2001",

month = mar,

doi = "10.1016/S0167-8655(00)00134-3",

language = "???core.languages.en_GB???",

volume = "22",

pages = "353--358",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

number = "3-4",

}

TY - JOUR

T1 - Application of the variance compensation likelihood measure for robust hidden Markov model in noise

AU - Huang, Kuo Chang

AU - Tung, Shin Lun

AU - Juang, Yau Tarng

N1 - Funding Information: This work was partially supported by the National Science Council of the Republic of China under the contract no. NSC88-2213-E-008-024.

PY - 2001/3

Y1 - 2001/3

N2 - This letter presents covariance matrix adaptation based upon the incorporation of the projection-based group delay scheme (PGDS) with a semi-continuous hidden Markov model (HMM) for the minimization of undesirable effects in noisy environments. The proposed approach fits the covariance matrix using a variance adaptive function to balance the mismatch between different environments.

AB - This letter presents covariance matrix adaptation based upon the incorporation of the projection-based group delay scheme (PGDS) with a semi-continuous hidden Markov model (HMM) for the minimization of undesirable effects in noisy environments. The proposed approach fits the covariance matrix using a variance adaptive function to balance the mismatch between different environments.

KW - Group delay scheme

KW - Hidden Markov model

KW - Mean compensation bias

KW - Projection measure

KW - Variance adaptive fuction

UR - http://www.scopus.com/inward/record.url?scp=0035271585&partnerID=8YFLogxK

U2 - 10.1016/S0167-8655(00)00134-3

DO - 10.1016/S0167-8655(00)00134-3

M3 - 期刊論文

AN - SCOPUS:0035271585

VL - 22

SP - 353

EP - 358

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 3-4

ER -

Application of the variance compensation likelihood measure for robust hidden Markov model in noise

Abstract

Keywords

Access to Document

Fingerprint

Cite this