Linear discriminant feature extraction using weighted classification confusion information

Hung Shin Lee, Berlin Chen

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Linear discriminant analysis (LDA) can be viewed as a two-stage procedure geometrically. The first stage conducts an orthogonal and whitening transformation of the variables. The second stage involves a principal component analysis (PCA) on the transformed class means, which is intended to maximize the class separability along the principal axes. In this paper, we demonstrate that the second stage does not necessarily guarantee better classification accuracy. Furthermore, we propose a generalization of LDA, weighted LDA (WLDA), by integrating the empirical classification confusion information between each class pair, such that the separability and the classification error rate can be taken into consideration simultaneously. WLDA can be efficiently solved by a lightweight eigen-decomposition and easily combined with other modifications to the LDA criterion. The experiment results show that WLDA can yield a relative character error reduction of 4.6% over LDA on the Mandarin LVCSR task.

Original languageEnglish
Pages (from-to)2254-2257
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2008

Fingerprint

Discriminant Analysis
Discriminant analysis
Feature extraction
Principal Component Analysis
Principal component analysis
Decomposition
Experiments

Keywords

  • Confusion information
  • Feature extraction
  • Linear discriminant analysis
  • Speech recognition

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Sensory Systems

Cite this

@article{d07418791a1e4230a2d567e956ccd80a,
title = "Linear discriminant feature extraction using weighted classification confusion information",
abstract = "Linear discriminant analysis (LDA) can be viewed as a two-stage procedure geometrically. The first stage conducts an orthogonal and whitening transformation of the variables. The second stage involves a principal component analysis (PCA) on the transformed class means, which is intended to maximize the class separability along the principal axes. In this paper, we demonstrate that the second stage does not necessarily guarantee better classification accuracy. Furthermore, we propose a generalization of LDA, weighted LDA (WLDA), by integrating the empirical classification confusion information between each class pair, such that the separability and the classification error rate can be taken into consideration simultaneously. WLDA can be efficiently solved by a lightweight eigen-decomposition and easily combined with other modifications to the LDA criterion. The experiment results show that WLDA can yield a relative character error reduction of 4.6{\%} over LDA on the Mandarin LVCSR task.",
keywords = "Confusion information, Feature extraction, Linear discriminant analysis, Speech recognition",
author = "Lee, {Hung Shin} and Berlin Chen",
year = "2008",
language = "English",
pages = "2254--2257",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - Linear discriminant feature extraction using weighted classification confusion information

AU - Lee, Hung Shin

AU - Chen, Berlin

PY - 2008

Y1 - 2008

N2 - Linear discriminant analysis (LDA) can be viewed as a two-stage procedure geometrically. The first stage conducts an orthogonal and whitening transformation of the variables. The second stage involves a principal component analysis (PCA) on the transformed class means, which is intended to maximize the class separability along the principal axes. In this paper, we demonstrate that the second stage does not necessarily guarantee better classification accuracy. Furthermore, we propose a generalization of LDA, weighted LDA (WLDA), by integrating the empirical classification confusion information between each class pair, such that the separability and the classification error rate can be taken into consideration simultaneously. WLDA can be efficiently solved by a lightweight eigen-decomposition and easily combined with other modifications to the LDA criterion. The experiment results show that WLDA can yield a relative character error reduction of 4.6% over LDA on the Mandarin LVCSR task.

AB - Linear discriminant analysis (LDA) can be viewed as a two-stage procedure geometrically. The first stage conducts an orthogonal and whitening transformation of the variables. The second stage involves a principal component analysis (PCA) on the transformed class means, which is intended to maximize the class separability along the principal axes. In this paper, we demonstrate that the second stage does not necessarily guarantee better classification accuracy. Furthermore, we propose a generalization of LDA, weighted LDA (WLDA), by integrating the empirical classification confusion information between each class pair, such that the separability and the classification error rate can be taken into consideration simultaneously. WLDA can be efficiently solved by a lightweight eigen-decomposition and easily combined with other modifications to the LDA criterion. The experiment results show that WLDA can yield a relative character error reduction of 4.6% over LDA on the Mandarin LVCSR task.

KW - Confusion information

KW - Feature extraction

KW - Linear discriminant analysis

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=84867192980&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867192980&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84867192980

SP - 2254

EP - 2257

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SN - 2308-457X

ER -