A Speech Enhancement Method Based on Multi-Task Bayesian Compressive Sensing

Hanxu YOU; Zhixian MA; Wei LI; Jie ZHU

doi:10.1587/transinf.2016EDP7350

A Speech Enhancement Method Based on Multi-Task Bayesian Compressive Sensing

Hanxu YOU, Zhixian MA, Wei LI, Jie ZHU

Full Text Views

0

Share
Cite this

Summary :

Traditional speech enhancement (SE) algorithms usually have fluctuant performance when they deal with different types of noisy speech signals. In this paper, we propose multi-task Bayesian compressive sensing based speech enhancement (MT-BCS-SE) algorithm to achieve not only comparable performance to but also more stable performance than traditional SE algorithms. MT-BCS-SE algorithm utilizes the dependence information among compressive sensing (CS) measurements and the sparsity of speech signals to perform SE. To obtain sufficient sparsity of speech signals, we adopt overcomplete dictionary to transform speech signals into sparse representations. K-SVD algorithm is employed to learn various overcomplete dictionaries. The influence of the overcomplete dictionary on MT-BCS-SE algorithm is evaluated through large numbers of experiments, so that the most suitable dictionary could be adopted by MT-BCS-SE algorithm for obtaining the best performance. Experiments were conducted on well-known NOIZEUS corpus to evaluate the performance of the proposed algorithm. In these cases of NOIZEUS corpus, MT-BCS-SE is shown that to be competitive or even superior to traditional SE algorithms, such as optimally-modified log-spectral amplitude (OMLSA), multi-band spectral subtraction (SSMul), and minimum mean square error (MMSE), in terms of signal-noise ratio (SNR), speech enhancement gain (SEG) and perceptual evaluation of speech quality (PESQ) and to have better stability than traditional SE algorithms.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.3 pp.556-563

Publication Date: 2017/03/01

Publicized: 2016/11/30

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDP7350

Type of Manuscript: PAPER

Category: Speech and Hearing

Authors

Hanxu YOU
  Shanghai Jiao Tong University (SJTU)
Zhixian MA
  Shanghai Jiao Tong University (SJTU)
Wei LI
  Shanghai Jiao Tong University (SJTU)
Jie ZHU
  Shanghai Jiao Tong University (SJTU)

Keyword

speech enhancement, compressive sensing, overcomplete dictionary, sparse representation

Cite this

Copy

Hanxu YOU, Zhixian MA, Wei LI, Jie ZHU, "A Speech Enhancement Method Based on Multi-Task Bayesian Compressive Sensing" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 3, pp. 556-563, March 2017, doi: 10.1587/transinf.2016EDP7350.
Abstract: Traditional speech enhancement (SE) algorithms usually have fluctuant performance when they deal with different types of noisy speech signals. In this paper, we propose multi-task Bayesian compressive sensing based speech enhancement (MT-BCS-SE) algorithm to achieve not only comparable performance to but also more stable performance than traditional SE algorithms. MT-BCS-SE algorithm utilizes the dependence information among compressive sensing (CS) measurements and the sparsity of speech signals to perform SE. To obtain sufficient sparsity of speech signals, we adopt overcomplete dictionary to transform speech signals into sparse representations. K-SVD algorithm is employed to learn various overcomplete dictionaries. The influence of the overcomplete dictionary on MT-BCS-SE algorithm is evaluated through large numbers of experiments, so that the most suitable dictionary could be adopted by MT-BCS-SE algorithm for obtaining the best performance. Experiments were conducted on well-known NOIZEUS corpus to evaluate the performance of the proposed algorithm. In these cases of NOIZEUS corpus, MT-BCS-SE is shown that to be competitive or even superior to traditional SE algorithms, such as optimally-modified log-spectral amplitude (OMLSA), multi-band spectral subtraction (SSMul), and minimum mean square error (MMSE), in terms of signal-noise ratio (SNR), speech enhancement gain (SEG) and perceptual evaluation of speech quality (PESQ) and to have better stability than traditional SE algorithms.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7350/_p

Copy

@ARTICLE{e100-d_3_556,
author={Hanxu YOU, Zhixian MA, Wei LI, Jie ZHU, },
journal={IEICE TRANSACTIONS on Information},
title={A Speech Enhancement Method Based on Multi-Task Bayesian Compressive Sensing},
year={2017},
volume={E100-D},
number={3},
pages={556-563},
abstract={Traditional speech enhancement (SE) algorithms usually have fluctuant performance when they deal with different types of noisy speech signals. In this paper, we propose multi-task Bayesian compressive sensing based speech enhancement (MT-BCS-SE) algorithm to achieve not only comparable performance to but also more stable performance than traditional SE algorithms. MT-BCS-SE algorithm utilizes the dependence information among compressive sensing (CS) measurements and the sparsity of speech signals to perform SE. To obtain sufficient sparsity of speech signals, we adopt overcomplete dictionary to transform speech signals into sparse representations. K-SVD algorithm is employed to learn various overcomplete dictionaries. The influence of the overcomplete dictionary on MT-BCS-SE algorithm is evaluated through large numbers of experiments, so that the most suitable dictionary could be adopted by MT-BCS-SE algorithm for obtaining the best performance. Experiments were conducted on well-known NOIZEUS corpus to evaluate the performance of the proposed algorithm. In these cases of NOIZEUS corpus, MT-BCS-SE is shown that to be competitive or even superior to traditional SE algorithms, such as optimally-modified log-spectral amplitude (OMLSA), multi-band spectral subtraction (SSMul), and minimum mean square error (MMSE), in terms of signal-noise ratio (SNR), speech enhancement gain (SEG) and perceptual evaluation of speech quality (PESQ) and to have better stability than traditional SE algorithms.},
keywords={},
doi={10.1587/transinf.2016EDP7350},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - A Speech Enhancement Method Based on Multi-Task Bayesian Compressive Sensing
T2 - IEICE TRANSACTIONS on Information
SP - 556
EP - 563
AU - Hanxu YOU
AU - Zhixian MA
AU - Wei LI
AU - Jie ZHU
PY - 2017
DO - 10.1587/transinf.2016EDP7350
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2017
AB - Traditional speech enhancement (SE) algorithms usually have fluctuant performance when they deal with different types of noisy speech signals. In this paper, we propose multi-task Bayesian compressive sensing based speech enhancement (MT-BCS-SE) algorithm to achieve not only comparable performance to but also more stable performance than traditional SE algorithms. MT-BCS-SE algorithm utilizes the dependence information among compressive sensing (CS) measurements and the sparsity of speech signals to perform SE. To obtain sufficient sparsity of speech signals, we adopt overcomplete dictionary to transform speech signals into sparse representations. K-SVD algorithm is employed to learn various overcomplete dictionaries. The influence of the overcomplete dictionary on MT-BCS-SE algorithm is evaluated through large numbers of experiments, so that the most suitable dictionary could be adopted by MT-BCS-SE algorithm for obtaining the best performance. Experiments were conducted on well-known NOIZEUS corpus to evaluate the performance of the proposed algorithm. In these cases of NOIZEUS corpus, MT-BCS-SE is shown that to be competitive or even superior to traditional SE algorithms, such as optimally-modified log-spectral amplitude (OMLSA), multi-band spectral subtraction (SSMul), and minimum mean square error (MMSE), in terms of signal-noise ratio (SNR), speech enhancement gain (SEG) and perceptual evaluation of speech quality (PESQ) and to have better stability than traditional SE algorithms.
ER -