基于稀疏编码的广义旁瓣抵消器语音增强算法

Li-chun YANG; Yun-tao QIAN

doi:10.1631/jzus.C1400085

Your Location：

Home >

Browse articles >

基于稀疏编码的广义旁瓣抵消器语音增强算法

电子工程 | Updated：2022-05-19

- 基于稀疏编码的广义旁瓣抵消器语音增强算法
- Speech enhancement with a GSC-like structure employing sparse coding
- 信息与电子工程前沿（英文） 2014年15卷第12期页码：1154-1163
- Affiliations：
  
  1.College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
  2.Intelligent Control Research Institute, Zhejiang Wanli University, Ningbo 315101, China
- Author bio：
  
  [ "Li-chun YANG, E-mail: lichun_y@126.com" ]
  Yun-tao QIAN, E-mail:ytqian@zju.edu.cn
- Funds：
  
  Project supported by the National Basic Research Program (973) of China (No. 2012CB316400) and the National Natural Science Foundation of China (No. 61171151)
- DOI：10.1631/jzus.C1400085
  中图分类号： TN912.35
- 收稿：2014-03-09，
  
  修回：2014-11-;9，
  
  纸质出版：2014-12
- Accepted：
Scan QR Code
基于稀疏编码的广义旁瓣抵消器语音增强算法[J]. 信息与电子工程前沿（英文）, 2014,15(12):1154-1163.

Li-chun YANG, Yun-tao QIAN. Speech enhancement with a GSC-like structure employing sparse coding[J]. Frontiers of Information Technology & Electronic Engineering, 2014, 15(12): 1154-1163.
基于稀疏编码的广义旁瓣抵消器语音增强算法[J]. 信息与电子工程前沿（英文）, 2014,15(12):1154-1163. DOI： 10.1631/jzus.C1400085.

Li-chun YANG, Yun-tao QIAN. Speech enhancement with a GSC-like structure employing sparse coding[J]. Frontiers of Information Technology & Electronic Engineering, 2014, 15(12): 1154-1163. DOI： 10.1631/jzus.C1400085.

摘要

研究目的

在广义旁瓣抵消器中，利用阻塞矩阵阻塞目标信号得到参考干扰信号，以便估计干扰信号，因此需尽量降低泄漏进参考干扰信号的目标信号。本文使用稀疏编码方法重构通过阻塞矩阵得到的参考干扰信号，以抑制目标干扰信号的泄漏，从而在较小语音失真情况下实现更有效的语音增强。

创新要点

利用非语音段干扰信号作为样本，训练得到干扰信号字典，用以重构参考干扰信号中的干扰信号，而目标信号由于与干扰信号不相关，可以被抑制。本文算法在传统阻塞矩阵基础上，加入干扰信号稀疏编码，实现了抑制残余目标信号的目的。

方法提亮

基于稀疏编码的广义旁瓣抵消器具有如下两个特点：一是利用非随机干扰信号结构相对稳定的特性，利用非语音段学习得到干扰信号字典，该字典与参考干扰信号结构特征相关，从而可用于对参考干扰信号的稀疏重构；二是克服了传统方法中单纯使用阻塞矩阵难以有效避免目标信号泄漏的不足，利用干扰信号字典进行稀疏编码，以抑制泄漏的少量残余目标信号的影响。

重要结论

本文提出的基于稀疏编码的参考干扰信号重构方法，可有效抑制参考干扰信号中的少量泄漏目标信号，利用自适应滤波估计得到较为准确的原始干扰信号，可以在目标语音失真度较小的情况下，实现对干扰信号最大程度的抑制。

Abstract

Speech communication is often influenced by various types of interfering signals. To improve the quality of the desired signal

a generalized sidelobe canceller (GSC)

which uses a reference signal to estimate the interfering signal

is attracting attention of researchers. However

the interference suppression of GSC is limited since a little residual desired signal leaks into the reference signal. To overcome this problem

we use sparse coding to suppress the residual desired signal while preserving the reference signal. Sparse coding with the learned dictionary is usually used to reconstruct the desired signal. As the training samples of a desired signal for dictionary learning are not observable in the real environment

the reconstructed desired signal may contain a lot of residual interfering signal. In contrast

the training samples of the interfering signal during the absence of the desired signal for interferer dictionary learning can be achieved through voice activity detection (VAD). Since the reference signal of an interfering signal is coherent to the interferer dictionary

it can be well restructured by sparse coding

while the residual desired signal will be removed. The performance of GSC will be improved since the estimate of the interfering signal with the proposed reference signal is more accurate than ever. Simulation and experiments on a real acoustic environment show that our proposed method is effective in suppressing interfering signals.

关键词

Keywords

references

A.M. Aharon , , , M. Elad . . K -SVD: an algorithm for designing overcomplete dictionaries for sparse representation . . IEEE Trans. Signal Process. , , 2006 . . 54 ( ( 11 ): ): 4311 - - 4322 . . DOI: 10.1109/TSP.2006.881199 http://doi.org/10.1109/TSP.2006.881199 . .

Y. Avargel , , , I. Cohen . . Adaptive system identification in the short-time fourier transform domain using cross-multiplicative transfer function approximation . . IEEE Trans. Audio Speech Lang. Process. , , 2008 . . 16 ( ( 1 ): ): 162 - - 173 . . DOI: 10.1109/TASL.2007.910789 http://doi.org/10.1109/TASL.2007.910789 . .

M. Elad , , , M. Aharon . . Image denoising via sparse and redundant representations over learned dictionaries . . IEEE Trans. Image Process. , , 2006 . . 15 ( ( 12 ): ): 3736 - - 3745 . . DOI: 10.1109/TIP.2006.881969 http://doi.org/10.1109/TIP.2006.881969 . .

K. Engan , , , K. Skretting , , , J.H. Husøy . . Family of iterative LS-based dictionary learning algorithms, ILS-DLA, for sparse signal representation . . Dig. Signal Process. , , 2007 . . 17 ( ( 1 ): ): 32 - - 49 . . DOI: 10.1016/j.dsp.2006.02.002 http://doi.org/10.1016/j.dsp.2006.02.002 . .

M. Eshaghi , , , M. Karami Mollaei . . Voice activity detection based on using wavelet packet . . Dig. Signal Process. , , 2010 . . 20 ( ( 4 ): ): 1102 - - 1115 . . DOI: 10.1016/j.dsp.2009.11.008 http://doi.org/10.1016/j.dsp.2009.11.008 . .

S. Gannot , , , D. Burshtein , , , E. Weinstein . . Signal enhancement using beamforming and nonstationarity with applications to speech . . IEEE Trans. Signal Process. , , 2001 . . 49 ( ( 8 ): ): 1614 - - 1626 . . DOI: 10.1109/78.934132 http://doi.org/10.1109/78.934132 . .

J.F. Gemmeke , , , B. Cranen . . Sparse imputation for noise robust speech recognition using soft masks . . IEEE Int. Conf. on Acoustics, Speech and Signal Processing , , 2009 . . p.4645 - - 4648 . . DOI: 10.1109/ICASSP.2009.4960666 http://doi.org/10.1109/ICASSP.2009.4960666 . .

R. Gribonval , , , K. Schnass . . Some recovery conditions for basis learning by ℓ 1 -minimization . . IEEE 3rd Int. Symp. on Communications, Control and Signal Processing , , 2008 . . p.768 - - 773 . . DOI: 10.1109/ISCCSP.2008.4537326 http://doi.org/10.1109/ISCCSP.2008.4537326 . .

L. Griffiths , , , C. Jim . . An alternative approach to linearly constrained adaptive beamforming . . IEEE Trans. Antennas Propag. , , 1982 . . 30 ( ( 1 ): ): 27 - - 34 . . DOI: 10.110/TAP.1982.1142739 http://doi.org/10.110/TAP.1982.1142739 . .

E.A.P. Habets . . Room Impulse Response Generator for MATLAB . . Univeristy of Erlangen-Nuremberg, Bavaria, Germany , , 2010 . . .

Y. He , , , J. Han , , , S. Deng , , , 等 . . A solution to residual noise in speech denoising with sparse representation . . EEE Int. Conf. on Acoustics, Speech and Signal Processing , , 2012 . . p.4653 - - 4656 . . DOI: 10.110/ICASSP.2012.6288956 http://doi.org/10.110/ICASSP.2012.6288956 . .

W. Herbordt , , , W. Kellermann . . Efficient frequency-domain realization of robust generalized sidelobe cancellers . . IEEE 4th Workshop on Multimedia Signal Processing , , 2001 . . p.377 - - 382 . . DOI: 10.1109/MMSP.2001.962763 http://doi.org/10.1109/MMSP.2001.962763 . .

O. Hoshuyama , , , A. Sugiyama , , , A. Hirano . . A robust adaptive beamformer for microphone arrays with a blocking matrix using constrained adaptive filters . . IEEE Trans. Signal Process. , , 1999 . . 47 ( ( 10 ): ): 2677 - - 2684 . . DOI: 10.1109/78.790650 http://doi.org/10.1109/78.790650 . .

ITU . . Wideband Extension to Rec. P.862 for the Assessment of Wideband Telephone Networks and Speech Codecs, P.862.2 . . International Telecommunication Union, Geneva , , 2007 . . .

M. Kowalski , , , B. Torrésani . . Random models for sparse signals expansion on unions of bases with application to audio signals . . IEEE Trans. Signal Process. , , 2008 . . 56 ( ( 8 ): ): 3468 - - 3481 . . DOI: 10.1109/TSP.2008.920144 http://doi.org/10.1109/TSP.2008.920144 . .

A. Krueger , , , E. Warsitz , , , R. Haeb-Umbach . . Speech enhancement with a GSC-like structure employing eigenvector-based transfer function ratios estimation . . IEEE Trans. Audio Speech Lang. Process. , , 2011 . . 19 ( ( 1 ): ): 206 - - 219 . . DOI: 10.1109/TASL.2010.2047324 http://doi.org/10.1109/TASL.2010.2047324 . .

J. Mairal , , , F. Bach , , , J. Ponce , , , 等 . . Online learning for matrix factorization and sparse coding . . J. Mach. Learn. Res. , , 2010 . . 11 19 - - 60 . . . .

R. Martin . . Noise power spectral density estimation based on optimal smoothing and minimum statistics . . IEEE Trans. Speech Audio Process. , , 2001 . . 9 ( ( 5 ): ): 504 - - 512 . . DOI: 10.1109/89.928915 http://doi.org/10.1109/89.928915 . .

R. Martin . . Bias compensation methods for minimum statistics noise power spectral density estimation . . Signal Process. , , 2006 . . 86 ( ( 6 ): ): 1215 - - 1229 . . DOI: 10.1016/j.sigpro.2005.07.037 http://doi.org/10.1016/j.sigpro.2005.07.037 . .

M.D. Plumbley , , , T. Blumensath , , , L. Daudet , , , 等 . . Sparse representations in audio and music: from coding to source separation . . Proc. IEEE , , 2010 . . 98 ( ( 6 ): ): 995 - - 1005 . . DOI: 10.1109/JPROC.2009.2030345 http://doi.org/10.1109/JPROC.2009.2030345 . .

H. Rauhut , , , K. Schnass , , , P. Vandergheynst . . Compressed sensing and redundant dictionaries . . IEEE Trans. Inform. Theory , , 2008 . . 54 ( ( 5 ): ): 2210 - - 2219 . . DOI: 10.110/TIT.2008.920190 http://doi.org/10.110/TIT.2008.920190 . .

L. Rebollo-Neira . . Dictionary redundancy elimination . . IEEE Proc.-Vis. Image Signal Process. , , 2004 . . 151 ( ( 1 ): ): 31 - - 34 . . DOI: 10.1049/ip-vis:20040294 http://doi.org/10.1049/ip-vis:20040294 . .

C.D. Sigg , , , T. Dikk , , , J.M. Buhmann . . Speech enhancement using generative dictionary learning . . IEEE Trans. Audio Speech Lang. Process. , , 2012 . . 20 ( ( 6 ): ): 1698 - - 1712 . . DOI: 10.1109/TASL.2012.2187194 http://doi.org/10.1109/TASL.2012.2187194 . .

K. Skretting , , , K. Engan . . Recursive least squares dictionary learning algorithm . . IEEE Trans. Signal Process. , , 2010 . . 58 ( ( 4 ): ): 2121 - - 2130 . . DOI: 10.1109/TSP.2010.2040671 http://doi.org/10.1109/TSP.2010.2040671 . .

J. Sohn , , , N.S. Kim , , , W. Sung . . A statistical model-based voice activity detection . . IEEE Signal Process. Lett. , , 1999 . . 6 ( ( 1 ): ): 1 - - 3 . . DOI: 10.1109/97.736233 http://doi.org/10.1109/97.736233 . .

R. Talmon , , , I. Cohen , , , S. Gannot . . Convolutive transfer function generalized sidelobe canceler . . IEEE Trans. Audio Speech Lang. Process. , , 2009 . . 17 ( ( 7 ): ): 1420 - - 1434 . . DOI: 10.1109/TASL.2009.2020891 http://doi.org/10.1109/TASL.2009.2020891 . .

S.G. Tanyer , , , H. Ozer . . Voice activity detection in nonstationary noise . . IEEE Trans. Speech Audio Process. , , 2000 . . 8 ( ( 4 ): ): 478 - - 482 . . DOI: 10.1109/89.848229 http://doi.org/10.1109/89.848229 . .

S.J. Wright , , , R.D. Nowak , , , M.A.T. Figueiredo . . Sparse reconstruction by separable approximation . . IEEE Trans. Signal Process. , , 2009 . . 57 ( ( 7 ): ): 2479 - - 2493 . . DOI: 10.110/TSP.2009.2016892]92 http://doi.org/10.110/TSP.2009.2016892]92 . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Kernel sparse representation for MRI image analysis in automatic brain tumor segmentation

Laplacian sparse dictionary learning for image classification based on sparse representation