Low-distortion MMSE speech enhancement estimator based on laplacian prior
The most well-known conventional speech enhancement algorithms introduce unwanted artifact noise and speech distortion to the enhanced signal. Reducing the effects of such issues require more robust linear and non-linear estimators. This paper proposes new optimum linear and non-linear Laplacian...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers
2017
|
Online Access: | http://psasir.upm.edu.my/id/eprint/62322/1/Low-distortion%20MMSE%20speech%20enhancement%20estimator%20based%20on%20laplacian%20prior.pdf |
_version_ | 1796977608816066560 |
---|---|
author | Mahmmod, Basheera M. Ramli, Abd Rahman Abdulhussain, Sadiq H. Syed Mohamed, Syed Abdul Rahman Al-Haddad A. Jassim, Wissam |
author_facet | Mahmmod, Basheera M. Ramli, Abd Rahman Abdulhussain, Sadiq H. Syed Mohamed, Syed Abdul Rahman Al-Haddad A. Jassim, Wissam |
author_sort | Mahmmod, Basheera M. |
collection | UPM |
description | The most well-known conventional speech enhancement algorithms introduce unwanted
artifact noise and speech distortion to the enhanced signal. Reducing the effects of such issues require
more robust linear and non-linear estimators. This paper proposes new optimum linear and non-linear
Laplacian distribution-based estimators. The proposed estimators are derived based on a minimum mean
squared error (MMSE) sense to minimize the distortion in different conditions of the underlying speech.
Thus, artifact noise is reduced without compromising the noise reduction process. The analytical solutions
of the Laplacian distribution-based estimators, linear bilateral Laplacian gain estimator (LBLG), and nonlinear bilateral Laplacian gain estimator (NBLG), are presented. The proposed estimators are implemented
in three steps. First, the observation signal is decorrelated through a real transform domain to obtain its
transform coefficients. Second, the proposed estimators are applied to estimate the clean speech signal from
the noisy signal in the decorrelated domain. Finally, the inverse of the real transform is applied to obtain the
original speech signal in the time domain. Two conditions in these estimators account for interference events
between the speech signal and noise coefficients in the decorrelated domain. Moreover, a mathematical
aspect of mean square error of LBLG is evaluated, which presents a significant improvement over other
methods. Furthermore, a comprehensive description of the whole variations of the LBLG and NBLG
gains characteristics is presented. A comparative evaluation is performed with effective quality metrics,
segmental signal-to-noise ratio and perceptual evaluation of speech quality, to demonstrate the advantage
and effectiveness of the proposed estimators. The performance of the proposed estimators outperformed
other methods, which are the traditional MMSE approach, perceptually motivated Bayesian estimator, dual
gain Wiener estimator, and dual MMSE estimator in terms of different objective measurements. |
first_indexed | 2024-03-06T09:42:35Z |
format | Article |
id | upm.eprints-62322 |
institution | Universiti Putra Malaysia |
language | English |
last_indexed | 2024-03-06T09:42:35Z |
publishDate | 2017 |
publisher | Institute of Electrical and Electronics Engineers |
record_format | dspace |
spelling | upm.eprints-623222019-10-31T04:19:22Z http://psasir.upm.edu.my/id/eprint/62322/ Low-distortion MMSE speech enhancement estimator based on laplacian prior Mahmmod, Basheera M. Ramli, Abd Rahman Abdulhussain, Sadiq H. Syed Mohamed, Syed Abdul Rahman Al-Haddad A. Jassim, Wissam The most well-known conventional speech enhancement algorithms introduce unwanted artifact noise and speech distortion to the enhanced signal. Reducing the effects of such issues require more robust linear and non-linear estimators. This paper proposes new optimum linear and non-linear Laplacian distribution-based estimators. The proposed estimators are derived based on a minimum mean squared error (MMSE) sense to minimize the distortion in different conditions of the underlying speech. Thus, artifact noise is reduced without compromising the noise reduction process. The analytical solutions of the Laplacian distribution-based estimators, linear bilateral Laplacian gain estimator (LBLG), and nonlinear bilateral Laplacian gain estimator (NBLG), are presented. The proposed estimators are implemented in three steps. First, the observation signal is decorrelated through a real transform domain to obtain its transform coefficients. Second, the proposed estimators are applied to estimate the clean speech signal from the noisy signal in the decorrelated domain. Finally, the inverse of the real transform is applied to obtain the original speech signal in the time domain. Two conditions in these estimators account for interference events between the speech signal and noise coefficients in the decorrelated domain. Moreover, a mathematical aspect of mean square error of LBLG is evaluated, which presents a significant improvement over other methods. Furthermore, a comprehensive description of the whole variations of the LBLG and NBLG gains characteristics is presented. A comparative evaluation is performed with effective quality metrics, segmental signal-to-noise ratio and perceptual evaluation of speech quality, to demonstrate the advantage and effectiveness of the proposed estimators. The performance of the proposed estimators outperformed other methods, which are the traditional MMSE approach, perceptually motivated Bayesian estimator, dual gain Wiener estimator, and dual MMSE estimator in terms of different objective measurements. Institute of Electrical and Electronics Engineers 2017 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/62322/1/Low-distortion%20MMSE%20speech%20enhancement%20estimator%20based%20on%20laplacian%20prior.pdf Mahmmod, Basheera M. and Ramli, Abd Rahman and Abdulhussain, Sadiq H. and Syed Mohamed, Syed Abdul Rahman Al-Haddad and A. Jassim, Wissam (2017) Low-distortion MMSE speech enhancement estimator based on laplacian prior. IEEE Access, 5. 9866 - 9881. ISSN 2169-3536 https://ieeexplore.ieee.org/document/7914629 |
spellingShingle | Mahmmod, Basheera M. Ramli, Abd Rahman Abdulhussain, Sadiq H. Syed Mohamed, Syed Abdul Rahman Al-Haddad A. Jassim, Wissam Low-distortion MMSE speech enhancement estimator based on laplacian prior |
title | Low-distortion MMSE speech enhancement estimator based on laplacian prior |
title_full | Low-distortion MMSE speech enhancement estimator based on laplacian prior |
title_fullStr | Low-distortion MMSE speech enhancement estimator based on laplacian prior |
title_full_unstemmed | Low-distortion MMSE speech enhancement estimator based on laplacian prior |
title_short | Low-distortion MMSE speech enhancement estimator based on laplacian prior |
title_sort | low distortion mmse speech enhancement estimator based on laplacian prior |
url | http://psasir.upm.edu.my/id/eprint/62322/1/Low-distortion%20MMSE%20speech%20enhancement%20estimator%20based%20on%20laplacian%20prior.pdf |
work_keys_str_mv | AT mahmmodbasheeram lowdistortionmmsespeechenhancementestimatorbasedonlaplacianprior AT ramliabdrahman lowdistortionmmsespeechenhancementestimatorbasedonlaplacianprior AT abdulhussainsadiqh lowdistortionmmsespeechenhancementestimatorbasedonlaplacianprior AT syedmohamedsyedabdulrahmanalhaddad lowdistortionmmsespeechenhancementestimatorbasedonlaplacianprior AT ajassimwissam lowdistortionmmsespeechenhancementestimatorbasedonlaplacianprior |