Subband-based blind signal separation for noisy speech recognition

Hyung Min Park; Ho Young Jung; Te Won Lee; Soo Young Lee

doi:10.1049/el:19991358

Subband-based blind signal separation for noisy speech recognition

Hyung Min Park, Ho Young Jung, Te Won Lee, Soo Young Lee

School of Electronics Engineering

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

44 Scopus citations

Abstract

A method for directly extracting clean speech features from noisy speech is proposed. This process is based on independent component analysis (ICA) and a new feature analysis technique for reducing the computational complexity of the frequency-domain ICA. For noisy speech signals recorded in real environments, this method yielded a considerable performance improvement.

Original language	English
Pages (from-to)	2011-2012
Number of pages	2
Journal	Electronics Letters
Volume	35
Issue number	23
DOIs	https://doi.org/10.1049/el:19991358
State	Published - 11 Nov 1999

Access to Document

10.1049/el:19991358

Cite this

@article{a94332bc123b4673be74f69e58c8feab,

title = "Subband-based blind signal separation for noisy speech recognition",

abstract = "A method for directly extracting clean speech features from noisy speech is proposed. This process is based on independent component analysis (ICA) and a new feature analysis technique for reducing the computational complexity of the frequency-domain ICA. For noisy speech signals recorded in real environments, this method yielded a considerable performance improvement.",

author = "Park, {Hyung Min} and Jung, {Ho Young} and Lee, {Te Won} and Lee, {Soo Young}",

year = "1999",

month = nov,

day = "11",

doi = "10.1049/el:19991358",

language = "English",

volume = "35",

pages = "2011--2012",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley & Sons Inc.",

number = "23",

}

TY - JOUR

T1 - Subband-based blind signal separation for noisy speech recognition

AU - Park, Hyung Min

AU - Jung, Ho Young

AU - Lee, Te Won

AU - Lee, Soo Young

PY - 1999/11/11

Y1 - 1999/11/11

N2 - A method for directly extracting clean speech features from noisy speech is proposed. This process is based on independent component analysis (ICA) and a new feature analysis technique for reducing the computational complexity of the frequency-domain ICA. For noisy speech signals recorded in real environments, this method yielded a considerable performance improvement.

AB - A method for directly extracting clean speech features from noisy speech is proposed. This process is based on independent component analysis (ICA) and a new feature analysis technique for reducing the computational complexity of the frequency-domain ICA. For noisy speech signals recorded in real environments, this method yielded a considerable performance improvement.

UR - http://www.scopus.com/inward/record.url?scp=0033343361&partnerID=8YFLogxK

U2 - 10.1049/el:19991358

DO - 10.1049/el:19991358

M3 - Article

AN - SCOPUS:0033343361

SN - 0013-5194

VL - 35

SP - 2011

EP - 2012

JO - Electronics Letters

JF - Electronics Letters

IS - 23

ER -

Subband-based blind signal separation for noisy speech recognition

Abstract

Access to Document

Other files and links

Fingerprint

Cite this