The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La soustraction spectrale est couramment utilisée pour l'amélioration de la parole dans un système monocanal en raison de la simplicité de sa mise en œuvre. Cependant, cet algorithme introduit un bruit musical perceptuel tout en supprimant le bruit de fond. Nous proposons dans cet article une approche basée sur les ondelettes pour supprimer le bruit de fond afin d'améliorer la parole dans un système à canal unique. La transformée en paquets d'ondelettes, qui émule le système auditif humain, est utilisée pour décomposer le signal bruité en bandes critiques. Le seuillage des ondelettes est ensuite ajusté temporellement avec la puissance du bruit par une estimation du bruit adaptée au temps. L'algorithme proposé peut supprimer efficacement le bruit tout en réduisant la distorsion de la parole. Les résultats expérimentaux, y compris plusieurs mesures objectives, montrent que l'algorithme proposé basé sur les ondelettes surpasse la soustraction spectrale et d'autres approches de débruitage basées sur les ondelettes pour l'amélioration de la parole dans les environnements bruyants non stationnaires.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Sheau-Fang LEI, Ying-Kai TUNG, "Wavelet-Based Speech Enhancement Using Time-Adapted Noise Estimation" in IEICE TRANSACTIONS on Fundamentals,
vol. E91-A, no. 9, pp. 2555-2563, September 2008, doi: 10.1093/ietfec/e91-a.9.2555.
Abstract: Spectral subtraction is commonly used for speech enhancement in a single channel system because of the simplicity of its implementation. However, this algorithm introduces perceptually musical noise while suppressing the background noise. We propose a wavelet-based approach in this paper for suppressing the background noise for speech enhancement in a single channel system. The wavelet packet transform, which emulates the human auditory system, is used to decompose the noisy signal into critical bands. Wavelet thresholding is then temporally adjusted with the noise power by time-adapted noise estimation. The proposed algorithm can efficiently suppress the noise while reducing speech distortion. Experimental results, including several objective measurements, show that the proposed wavelet-based algorithm outperforms spectral subtraction and other wavelet-based denoising approaches for speech enhancement for nonstationary noise environments.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.9.2555/_p
Copier
@ARTICLE{e91-a_9_2555,
author={Sheau-Fang LEI, Ying-Kai TUNG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Wavelet-Based Speech Enhancement Using Time-Adapted Noise Estimation},
year={2008},
volume={E91-A},
number={9},
pages={2555-2563},
abstract={Spectral subtraction is commonly used for speech enhancement in a single channel system because of the simplicity of its implementation. However, this algorithm introduces perceptually musical noise while suppressing the background noise. We propose a wavelet-based approach in this paper for suppressing the background noise for speech enhancement in a single channel system. The wavelet packet transform, which emulates the human auditory system, is used to decompose the noisy signal into critical bands. Wavelet thresholding is then temporally adjusted with the noise power by time-adapted noise estimation. The proposed algorithm can efficiently suppress the noise while reducing speech distortion. Experimental results, including several objective measurements, show that the proposed wavelet-based algorithm outperforms spectral subtraction and other wavelet-based denoising approaches for speech enhancement for nonstationary noise environments.},
keywords={},
doi={10.1093/ietfec/e91-a.9.2555},
ISSN={1745-1337},
month={September},}
Copier
TY - JOUR
TI - Wavelet-Based Speech Enhancement Using Time-Adapted Noise Estimation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2555
EP - 2563
AU - Sheau-Fang LEI
AU - Ying-Kai TUNG
PY - 2008
DO - 10.1093/ietfec/e91-a.9.2555
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2008
AB - Spectral subtraction is commonly used for speech enhancement in a single channel system because of the simplicity of its implementation. However, this algorithm introduces perceptually musical noise while suppressing the background noise. We propose a wavelet-based approach in this paper for suppressing the background noise for speech enhancement in a single channel system. The wavelet packet transform, which emulates the human auditory system, is used to decompose the noisy signal into critical bands. Wavelet thresholding is then temporally adjusted with the noise power by time-adapted noise estimation. The proposed algorithm can efficiently suppress the noise while reducing speech distortion. Experimental results, including several objective measurements, show that the proposed wavelet-based algorithm outperforms spectral subtraction and other wavelet-based denoising approaches for speech enhancement for nonstationary noise environments.
ER -