Improved speech recognition using a subspace projection approach

Philipos C. Loizou, Andreas Spanias

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Two class-separability criteria based on the divergence measure are proposed to improve speech recognition performance. The average and weighted average divergence measures are used as criteria for finding a transformation matrix which maps the original features into a more discriminative subspace. Results are presented for a highly confusable task.

Original languageEnglish (US)
Pages (from-to)343-345
Number of pages3
JournalIEEE Transactions on Speech and Audio Processing
Volume7
Issue number3
DOIs
StatePublished - 1999
Externally publishedYes

Fingerprint

speech recognition
Speech recognition
divergence
projection

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Improved speech recognition using a subspace projection approach. / Loizou, Philipos C.; Spanias, Andreas.

In: IEEE Transactions on Speech and Audio Processing, Vol. 7, No. 3, 1999, p. 343-345.

Research output: Contribution to journalArticle

@article{f0198764137c4afba53e27137f2a6fb0,
title = "Improved speech recognition using a subspace projection approach",
abstract = "Two class-separability criteria based on the divergence measure are proposed to improve speech recognition performance. The average and weighted average divergence measures are used as criteria for finding a transformation matrix which maps the original features into a more discriminative subspace. Results are presented for a highly confusable task.",
author = "Loizou, {Philipos C.} and Andreas Spanias",
year = "1999",
doi = "10.1109/89.759044",
language = "English (US)",
volume = "7",
pages = "343--345",
journal = "IEEE Transactions on Speech and Audio Processing",
issn = "1558-7916",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Improved speech recognition using a subspace projection approach

AU - Loizou, Philipos C.

AU - Spanias, Andreas

PY - 1999

Y1 - 1999

N2 - Two class-separability criteria based on the divergence measure are proposed to improve speech recognition performance. The average and weighted average divergence measures are used as criteria for finding a transformation matrix which maps the original features into a more discriminative subspace. Results are presented for a highly confusable task.

AB - Two class-separability criteria based on the divergence measure are proposed to improve speech recognition performance. The average and weighted average divergence measures are used as criteria for finding a transformation matrix which maps the original features into a more discriminative subspace. Results are presented for a highly confusable task.

UR - http://www.scopus.com/inward/record.url?scp=0032667670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032667670&partnerID=8YFLogxK

U2 - 10.1109/89.759044

DO - 10.1109/89.759044

M3 - Article

AN - SCOPUS:0032667670

VL - 7

SP - 343

EP - 345

JO - IEEE Transactions on Speech and Audio Processing

JF - IEEE Transactions on Speech and Audio Processing

SN - 1558-7916

IS - 3

ER -