Speech denoising algorithm based on singular spectrum analysis and Wiener filtering

doi:10.11772/j.issn.1001-9081.2015.08.2336

Journal of Computer Applications ›› 2015, Vol. 35 ›› Issue (8): 2336-2340.DOI: 10.11772/j.issn.1001-9081.2015.08.2336

Previous Articles Next Articles

Speech denoising algorithm based on singular spectrum analysis and Wiener filtering

JIN Liyan¹, CHEN Li¹, FAN Taiting², GAO Jing¹

1. School of Information Science and Technology, Northwest University, Xi'an Shaanxi 710127, China;
2. Xi'an Productivity Promotion Center, Xi'an Shaanxi 710048, China

Received:2015-03-16 Revised:2015-05-15 Online:2015-08-10 Published:2015-08-14

基于奇异谱分析和维纳滤波的语音去噪算法

靳立燕¹, 陈莉¹, 樊泰亭², 高晶¹

1. 西北大学信息科学与技术学院, 西安 710127;
2. 西安生产力促进中心, 西安 710048

通讯作者: 陈莉(1963-),女,陕西西安人,教授,博士生导师,博士,主要研究方向:数据挖掘、机器学习,chenli@nwu.edu.cn
作者简介:靳立燕(1989-),女,河北邢台人,硕士研究生,主要研究方向:数据挖掘、语音信号处理; 樊泰亭(1964-),男,山西夏县人,高级工程师,主要研究方向:数据库、信息处理;高晶(1990-),女,山西吕梁人,硕士研究生,主要研究方向:数据挖掘、图像处理。
基金资助:
国家科技支撑项目(2013BAH4902,2013BAH4903);国家自然科学基金资助项目(61379010)。

Abstract

Abstract:

Concerning that the Wiener filtering algorithm leads signal distortion with low Signal-to-Noise Ratio (SNR) when dealing with the noise of non-stationary speech signal, a new speech denoising algorithm named SSA-WF was proposed combining with Singular Spectrum Analysis (SSA) and Wiener Filtering (WF). To obtain the speech signal as smooth as possible, SSA was used to denoise the nonlinear and non-stationary speech signal to improve the SNR of the noisy speech. Then the processed signal was put into WF to further eliminate the high frequency noise that still existed in the speech signal. The simulation results from different intensity of background noise show that the proposed algorithm is superior to the traditional methods in SNR and Root-Mean-Square Error (RMSE). The results also demonstrate that the new algorithm can not only remove the background noise efficiently, but also reserve the details of the original signal, it is suitable for the denoising of nonlinear and non-stationary speech signal.

Key words: Singular Spectrum Analysis (SSA), Wiener Filtering (WF), speech signal, denoising, strong noise

摘要：

针对维纳滤波算法对非平稳语音信号去噪存在的信号失真、信噪比(SNR)不高的问题,提出了一种奇异谱分析(SSA)和维纳滤波(WF)相结合的语音去噪算法SSA-WF。通过奇异谱分析将非线性、非平稳的语音信号初步去噪,提高含噪语音的信噪比以获取尽可能平稳的语音,并将其作为维纳滤波的输入,以剔除其中仍存在的高频噪声,最终获取纯净的去噪语音。在不同强度的背景噪声下进行仿真实验,结果表明SSA-WF算法在SNR和均方根误差(RMSE)等方面都要优于传统的语音去噪算法,能够有效去除背景噪声,降低有用信号的失真,适用于非线性、非平稳语音信号的去噪。

关键词: 奇异谱分析, 维纳滤波, 语音信号, 去噪, 强噪声

CLC Number:

TN912.3

JIN Liyan, CHEN Li, FAN Taiting, GAO Jing. Speech denoising algorithm based on singular spectrum analysis and Wiener filtering[J]. Journal of Computer Applications, 2015, 35(8): 2336-2340.

靳立燕, 陈莉, 樊泰亭, 高晶. 基于奇异谱分析和维纳滤波的语音去噪算法[J]. 计算机应用, 2015, 35(8): 2336-2340.

References

[1] SUN L, YANG Z. Speech enhancement based on data-driven dictionary and sparse representation [J]. Signal Processing,2012, 27(12): 1793-1800. (孙林慧,杨震.基于数据驱动字典和稀疏表示的语音增强[J].信号处理,2012,27(12):1793-1800.)
[2] JIA H, REN Y, ZHANG X. An improved wavelet packet threshold function for speech enhancement method [J]. Journal of Information & Computational Science, 2013, 10(3): 941-948.
[3] WANG H, SHANG C, GAO R, et al. An improvement of wavelet shrinkage denoising via wavelet coefficient transformation [J]. Journal of Vibration and Shock,2011,30(10):165-168. (王宏强,尚春阳,高瑞鹏,等.基于小波系数变换的小波阈值去噪算法改进[J].振动与冲击,2011,30(10):165-168.)
[4] LI J, AN D, WANG J. Speech denoising method based on the EEMD and ICA approaches [J].Journal of Northwestern University: Natural Science,2011,32(11): 1554-1557. (李晶皎,安冬,王骄.基于EEMD和ICA的语音去噪方法[J].东北大学学报:自然科学版,2011,32(11):1554-1557.)
[5] MA Y, NISHIHARA A. A modified Wiener filtering method combined with wavelet thresholding multitaper spectrum for speech enhancement [J]. EURASIP Journal on Audio, Speech, and Music Processing, 2014, 2014: 32.
[6] LYU Z. Study of speech recognition algorithm under noise environment [D]. Hefei: Anhui University, 2011: 35-37. (吕钊.噪声环境下的语音识别算法研究[D].合肥:安徽大学,2011:35-37.)
[7] LEI J, YANG Z, LIU G, et al. Research on speech enhancement based on short-time spectrum estimation [J].Computer Engineering and Applications, 2009, 44(32): 6-9. (雷建军,杨震,刘刚,等.基于短时谱估计的语音增强研究[J].计算机工程与应用,2009,44(32):6-9.)
[8] CHENG C, HUANG L. Research on Speech enhancement based on Wiener filtering [J]. Applied Mechanics and Materials, 2014, (513/514/516/517): 3130-3133.
[9] EL-FATTAH M A A, DESSOUKY M I, ABBAS A M, et al. Speech enhancement with an adaptive Wiener filter [J]. International Journal of Speech Technology, 2014, 17(1): 53-64.
[10] BROOMHEAD D S, KING G P. Extracting qualitative dynamics from experimental data [J]. Physica D: Nonlinear Phenomena, 1986, 20(2/3): 217-236.
[11] LI N, DENG S, TANG Q. Speech enhancement algorithm based on combining local characteristic-scale decomposition and difference spectrum of singular values [J]. Journal of Multimedia, 2013, 8(3): 233-240.
[12] MA H, JIANG Q, LIU Z, et al. A novel blind source separation method for single-channel signal [J].Signal Processing, 2010, 90(12): 3232-3241.
[13] GUO F. Signal processing methods research in nonstationary nuclear magnetic resonance experiment [D]. Wuhan: Huazhong University of Science and Technology,2012:40-41. (郭峰.非稳态核磁共振实验中的若干信号处理技术研究[D].武汉:华中科技大学,2012:40-41.)
[14] LIU Y, ZHAO M. Denoising of chaotic time series based on singular spectrum analysis [J].Journal of Shanghai Jiaotong University,2003,37(5): 778-780. (刘元峰, 赵玫. 基于奇异谱分析的混沌序列降噪[J].上海交通大学学报,2003,37(5):778-780.)
[15] LU D, GUO X. Wavelet packet denoising algorithm for heart sound signal based on singular spectrum analysis [J]. Journal of Vibration and Shock,2013,32(18):63-69. (卢德林,郭兴明.基于奇异谱分析的心音信号小波包去噪算法研究[J].振动与冲击,2013,32(18):63-69.)
[16] CAO L. Practical method for determining the minimum embedding dimension of a scalar time series [J]. Physica D: Nonlinear Phenomena,1997,110(1/2): 43-50.

Speech denoising algorithm based on singular spectrum analysis and Wiener filtering

基于奇异谱分析和维纳滤波的语音去噪算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	ZHANG Yuanjun, ZHANG Xihuang. Dynamic network representation learning model based on graph convolutional network and long short-term memory network [J]. Journal of Computer Applications, 2021, 41(7): 1857-1864.
[2]	JING Beibei, GUO Jia, WANG Liqing, CHEN Jing, DING Hongwei. Image double blind denoising algorithm combining with denoising convolutional neural network and conditional generative adversarial net [J]. Journal of Computer Applications, 2021, 41(6): 1767-1774.
[3]	LUO Jun, CHEN Lifei. Sentiment classification of incomplete data based on bidirectional encoder representations from transformers [J]. Journal of Computer Applications, 2021, 41(1): 139-144.
[4]	HU Xueying, GUO Hairu, ZHU Rong. Image super-resolution reconstruction based on hybrid deep convolutional network [J]. Journal of Computer Applications, 2020, 40(7): 2069-2076.
[5]	ZHU Zhe, XU Shaohua. Denoising autoencoder deep convolution process neural network and its application in time-varying signal classification [J]. Journal of Computer Applications, 2020, 40(3): 698-703.
[6]	FU Hongliang, LEI Peizhi. Speech deception detection algorithm based on denoising autoencoder and long short-term memory network [J]. Journal of Computer Applications, 2020, 40(2): 589-594.
[7]	WANG Haipeng, JIANG Ailian, LI Pengxiang. Newton-soft threshold iteration algorithm for robust principal component analysis [J]. Journal of Computer Applications, 2020, 40(11): 3133-3138.
[8]	WANG Yihao, DING Hongwei, LI Bo, BAO Liyong, ZHANG Yingjie. Prediction of protein subcellular localization based on deep learning [J]. Journal of Computer Applications, 2020, 40(11): 3393-3399.
[9]	WANG Zhizhong, LI Hongyi, HAN Chuang. QRS complex detection algorithm of electrocardiograph based on Shannon energy and adaptive threshold [J]. Journal of Computer Applications, 2020, 40(1): 304-310.
[10]	LAI Jie, WANG Xiaodan, LI Rui, ZHAO Zhenchong. Denoising autoencoder based extreme learning machine [J]. Journal of Computer Applications, 2019, 39(6): 1619-1625.
[11]	YANG Yang, WANG Zhengqun, XU Chunlin, YAN Chen, JU Ling. Robust multi-manifold discriminant local graph embedding based on maximum margin criterion [J]. Journal of Computer Applications, 2019, 39(5): 1453-1458.
[12]	GUO Xudong, LI Xiaomin, JING Ruxue, GAO Yuzhuo. Intrusion detection based on improved sparse denoising autoencoder [J]. Journal of Computer Applications, 2019, 39(3): 769-773.
[13]	TAO Yongpeng, JING Yu, XU Cong. Image denoising algorithm based on grouped dictionaries and variational model [J]. Journal of Computer Applications, 2019, 39(2): 551-555.
[14]	ZHANG Wenwen, HAN Yusheng. Nonlocal self-similarity based low-rank spase image denoising [J]. Journal of Computer Applications, 2018, 38(9): 2696-2700.
[15]	GUO Qingrong, JIA Zhenhong, YANG Jie, Nikola KASABOV. Synthetic aperture radar image enhancement method based on combination of non-subsampled shearlet transform and fuzzy contrast [J]. Journal of Computer Applications, 2018, 38(9): 2701-2705.