Speech enhancement with MAP estimation and ICA-based speech features

Jong Hwan Lee; Ho Young Jung; Te Won Lee; Soo Young Lee

doi:10.1049/el:20001028

Speech enhancement with MAP estimation and ICA-based speech features

Jong Hwan Lee
, Ho Young Jung
, Te Won Lee
, Soo Young Lee

School of Electronics Engineering

Korea Advanced Institute of Science and Technology
University of California at San Diego

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

12 Scopus citations

Abstract

The independent component analysis (ICA)-based speech features were used to remove Gaussian noise in the noisy speech signals using a maximum a posteriori (MAP) estimator. Speech signals corrupted by additive white Gaussian noise were recovered with greatly improved signal-to-noise ratio (SNR) values. Denoised spectral features also resulted in better recognition rates than the standard MFCC features.

Original language	English
Pages (from-to)	1506-1507
Number of pages	2
Journal	Electronics Letters
Volume	36
Issue number	17
DOIs	https://doi.org/10.1049/el:20001028
State	Published - 17 Aug 2000

Access to Document

10.1049/el:20001028

Cite this

@article{46cfbffd55a3476391ea965ac47e4da3,

title = "Speech enhancement with MAP estimation and ICA-based speech features",

abstract = "The independent component analysis (ICA)-based speech features were used to remove Gaussian noise in the noisy speech signals using a maximum a posteriori (MAP) estimator. Speech signals corrupted by additive white Gaussian noise were recovered with greatly improved signal-to-noise ratio (SNR) values. Denoised spectral features also resulted in better recognition rates than the standard MFCC features.",

author = "Lee, \{Jong Hwan\} and Jung, \{Ho Young\} and Lee, \{Te Won\} and Lee, \{Soo Young\}",

year = "2000",

month = aug,

day = "17",

doi = "10.1049/el:20001028",

language = "English",

volume = "36",

pages = "1506--1507",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley \& Sons Inc.",

number = "17",

}

TY - JOUR

T1 - Speech enhancement with MAP estimation and ICA-based speech features

AU - Lee, Jong Hwan

AU - Jung, Ho Young

AU - Lee, Te Won

AU - Lee, Soo Young

PY - 2000/8/17

Y1 - 2000/8/17

N2 - The independent component analysis (ICA)-based speech features were used to remove Gaussian noise in the noisy speech signals using a maximum a posteriori (MAP) estimator. Speech signals corrupted by additive white Gaussian noise were recovered with greatly improved signal-to-noise ratio (SNR) values. Denoised spectral features also resulted in better recognition rates than the standard MFCC features.

AB - The independent component analysis (ICA)-based speech features were used to remove Gaussian noise in the noisy speech signals using a maximum a posteriori (MAP) estimator. Speech signals corrupted by additive white Gaussian noise were recovered with greatly improved signal-to-noise ratio (SNR) values. Denoised spectral features also resulted in better recognition rates than the standard MFCC features.

UR - https://www.scopus.com/pages/publications/0034245955

U2 - 10.1049/el:20001028

DO - 10.1049/el:20001028

M3 - Article

AN - SCOPUS:0034245955

SN - 0013-5194

VL - 36

SP - 1506

EP - 1507

JO - Electronics Letters

JF - Electronics Letters

IS - 17

ER -

Speech enhancement with MAP estimation and ICA-based speech features

Abstract

Access to Document

Other files and links

Fingerprint

Cite this