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.
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.
Copy
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
Copy
@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},}
Copy
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 -