Heart sound denoising by dynamic noise estimation_Journal of Biomedical Engineering

Authors：

 XU Chundong ¹ , ZHOU Jing ¹ , YING Dongwen ^1,2 , XIN Pengli ¹

1. School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, P.R.China;
2. School of Electronic, Electronical, and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, P.R.China;

Corresponding author：

XU Chundong, Email: xuchundong@jxust.edu.cn

Keywords：

heart sound denoising; improved minimum control recursive average; optimally modified log-spectral amplitude; noise estimate; heart sound classification

DOI：

10.7507/1001-5515.202002023

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Denoising methods based on wavelet analysis and empirical mode decomposition cannot essentially track and eliminate noise, which usually cause distortion of heart sounds. Based on this problem, a heart sound denoising method based on improved minimum control recursive average and optimally modified log-spectral amplitude is proposed in this paper. The proposed method uses a short-time window to smoothly and dynamically track and estimate the minimum noise value. The noise estimation results are used to obtain the optimal spectrum gain function, and to minimize the noise by minimizing the difference between the clean heart sound and the estimated clean heart sound. In addition, combined with the subjective analysis of spectrum and the objective analysis of contribution to normal and abnormal heart sound classification system, we propose a more rigorous evaluation mechanism. The experimental results show that the proposed method effectively improves the time-frequency features, and obtains higher scores in the normal and abnormal heart sound classification systems. The proposed method can help medical workers to improve the accuracy of their diagnosis, and also has great reference value for the construction and application of computer-aided diagnosis system.

Citation： XU Chundong, ZHOU Jing, YING Dongwen, XIN Pengli. Heart sound denoising by dynamic noise estimation. Journal of Biomedical Engineering, 2020, 37(5): 775-785. doi: 10.7507/1001-5515.202002023 Copy

1.	Zhang Wenjie, Han Jiqing, Deng Shiwen. Heart sound classification based on scaled spectrogram and partial least squares regression. Biomed Signal Process Control, 2017, 32: 20-28.
2.	Raza A, Mehmood A, Ullah S, et al. Heartbeat sound signal classification using deep learning. Sensors (Basel), 2019, 19(21): 4819.
3.	Puneet K J, Tiwari A K. An adaptive thresholding method for the wavelet based denoising of phonocardiogram signal. Biomed Signal Process Control, 2017, 38: 388-399.
4.	Semmlow J L. Improved heart sound detection and signal-to-noise estimation using a low-mass sensor. IEEE Transactions on Biomedical Engineering, 2016, 63(3): 647-652.
5.	董利超, 郭兴明, 郑伊能. 基于CEEMD的心音信号小波包去噪算法研究. 振动与冲击, 2019, 38(9): 192-198, 222.
6.	Cheng Xiefeng, Zheng Zhang. Denoising method of heart sound signals based on self-construct heart sound wavelet. AIP Adv, 2014, 4(8): 87-108.
7.	Boutana D, Benidir M, Barkat B. On the selection of intrinsic mode function in EMD method: application on heart sound signal//2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL 2010), Rome: IEEE, 2010: 1-5.
8.	Zaid A, Ebrahim A N, Manal A W, et al. Classification of heart sounds using fractional Fourier transform based Mel-frequency spectral coefficients and stacked autoencoder deep neural network. J Med Imaging Health Inform, 2019, 9(1): 1-8.
9.	Oliveira J, Renna F, Coimbra M. A Subject-Driven unsupervised hidden Semi-Markov model and gaussian mixture model for heart sound segmentation. IEEE J Sel Top Signal Process, 2019, 13(2): 323-331.
10.	刘俏俏, 谭志向, 张懿, 等. 基于经验模态分解的胎心音信号除噪方法. 生物医学工程学杂志, 2015, 32(4): 740-745, 772.
11.	王娜. 基于小波变换与约束方差噪声谱估计的语音增强算法研究. 秦皇岛: 燕山大学, 2011.
12.	Brunetti N D, Rosania S, D'antuono C, et al. Diagnostic accuracy of heart murmur in newborns with suspected congenital heart disease. J Cardiovasc Med (Hagerstown), 2015, 16(8): 556-561.
13.	Premkumar P. Utility of echocardiogram in the evaluation of heart murmurs. Med Clin North Am, 2016, 100(5): 991-1001.
14.	Whitaker B M, Suresha P B, Liu C, et al. Combining sparse coding and time-domain features for heart sound classification. Physiol Meas, 2017, 38(8): 1701-1713.
15.	Chen Lingguang, Wu F S, Xu Yong,, et al. Blind separation of heart sounds. Journal of the Acoustical Society of America, 2017, 137(04): 2388-2388.
16.	许春冬, 周静, 龙清华, 等. 基于coif-5小波的心音自适应阈值降噪方法. 科学技术与工程, 2019, 19(2): 106-113.
17.	Yuan Wenhao, Lin Jiajun, Wei A N, et al. Noise estimation based on time–frequency correlation for speech enhancement. Applied Acoustics, 2013, 74(5): 770-781.
18.	Hirszhorn A, Dov D, Talmon R, et al. Transient interference suppression in speech signals based on the OM-LSA algorithm//International Workshop on Acoustic Signal Enhancement, Aachen: VDE, 2012: 1-4.
19.	袁文浩, 林家骏, 王雨, 等. 一种基于噪声分类的语音增强方法. 华东理工大学学报:自然科学版, 2014, 40(2): 196-201.
20.	曹克宇. 语音系统中瞬态噪声抑制算法的研究. 哈尔滨: 哈尔滨工业大学, 2017.
21.	陈成斌. 针对于家居环境的语音增强系统的研究与开发. 广州: 华南理工大学, 2015.
22.	刘凤增. 复杂环境下语音增强方法研究. 长沙: 国防科学技术大学, 2011.
23.	李国正, 谭南林, 苏树强, 等. 混沌同步系统降噪方法及其在滚动轴承故障诊断中的应用. 北京理工大学学报, 2019, 39(7): 669-675.
24.	Cohen I, Berdugo B. Speech enhancement for non-stationary noise environments. Signal Processing, 2001, 81(11): 2403-2418.
25.	Cohen I, Berdugo B. Spectral enhancement by tracking speech presence probability in subbands//IEEE Workshop on Hands-Free Speech Communication, Kyoto: IEEE, 2001: 95-98.
26.	Tran T D, Nguyen Q C, Nguyen D K. Speech enhancement using modified IMCRA and OMLSA methods//International Conference on Communications and Electronics 2010, Nha Trang: IEEE, 2010: 195-200.
27.	Ephraim H, Malah D. Speech enhancement using a minimum mean square error short-time spectral amplitude estimator. IEEE Transactions on Acoustics, Speech and Signal Processing, 1984, 32(06): 1109-1121.
28.	Hou Xuchu, Guo S, Cui H, et al. Speech enhancement for Non-Stationary noise environments//2009 International Conference on Information Engineering and Computer Science, Wuhan: IEEE, 2009: 1-3.
29.	Cohen I. Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging. IEEE Transactions on Speech and Audio Processing, 2003, 11(5): 466-475.
30.	熊晶. 语音增强中噪声估计的研究. 兰州: 兰州交通大学, 2015.
31.	Clifford G, Liu Chengyu, Moody B, et al. Classification of normal/abnormal heart sound recordings: the PhysioNet/computing in cardiology challenge 2016//2016 Computing in Cardiology Conference (CinC), 2016: 609-612.
32.	Liu C Y, Springer D, Li Q, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas, 2016, 37(12): 2181-2213.
33.	成谢锋, 陈亚敏. S1和S2共振峰频率在心音分类识别中的应用. 南京邮电大学学报:自然科学版, 2017, 37(5): 7-12.
34.	陈亚敏. 一种基于级联无损声管的心音产生模型的研究及应用. 南京: 南京邮电大学, 2017.
35.	Hong Tang, Chen Huaming, Li Ting, et al. Classification of normal/abnormal heart sound recordings based on multi-domain features and back propagation neural network//2016 Computing in Cardiology Conference (CinC), Vancouver: IEEE, 2016: 593-596.
36.	Springer D B, Tarassenko L, Clifford G D. Logistic Regression-HSMM-Based heart sound segmentation. IEEE Trans Biomed Eng, 2016, 63(4): 822-832.
37.	Bouril A, Aleinikava D, Guillem M S, et al. Automated classification of normal and abnormal heart sounds using support vector machines//2016 Computing in Cardiology Conference (CinC), Vancouver: IEEE, 2016: 549-552.

1. Zhang Wenjie, Han Jiqing, Deng Shiwen. Heart sound classification based on scaled spectrogram and partial least squares regression. Biomed Signal Process Control, 2017, 32: 20-28.
2. Raza A, Mehmood A, Ullah S, et al. Heartbeat sound signal classification using deep learning. Sensors (Basel), 2019, 19(21): 4819.
3. Puneet K J, Tiwari A K. An adaptive thresholding method for the wavelet based denoising of phonocardiogram signal. Biomed Signal Process Control, 2017, 38: 388-399.
4. Semmlow J L. Improved heart sound detection and signal-to-noise estimation using a low-mass sensor. IEEE Transactions on Biomedical Engineering, 2016, 63(3): 647-652.
5. 董利超, 郭兴明, 郑伊能. 基于CEEMD的心音信号小波包去噪算法研究. 振动与冲击, 2019, 38(9): 192-198, 222.
6. Cheng Xiefeng, Zheng Zhang. Denoising method of heart sound signals based on self-construct heart sound wavelet. AIP Adv, 2014, 4(8): 87-108.
7. Boutana D, Benidir M, Barkat B. On the selection of intrinsic mode function in EMD method: application on heart sound signal//2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL 2010), Rome: IEEE, 2010: 1-5.
8. Zaid A, Ebrahim A N, Manal A W, et al. Classification of heart sounds using fractional Fourier transform based Mel-frequency spectral coefficients and stacked autoencoder deep neural network. J Med Imaging Health Inform, 2019, 9(1): 1-8.
9. Oliveira J, Renna F, Coimbra M. A Subject-Driven unsupervised hidden Semi-Markov model and gaussian mixture model for heart sound segmentation. IEEE J Sel Top Signal Process, 2019, 13(2): 323-331.
10. 刘俏俏, 谭志向, 张懿, 等. 基于经验模态分解的胎心音信号除噪方法. 生物医学工程学杂志, 2015, 32(4): 740-745, 772.
11. 王娜. 基于小波变换与约束方差噪声谱估计的语音增强算法研究. 秦皇岛: 燕山大学, 2011.
12. Brunetti N D, Rosania S, D'antuono C, et al. Diagnostic accuracy of heart murmur in newborns with suspected congenital heart disease. J Cardiovasc Med (Hagerstown), 2015, 16(8): 556-561.
13. Premkumar P. Utility of echocardiogram in the evaluation of heart murmurs. Med Clin North Am, 2016, 100(5): 991-1001.
14. Whitaker B M, Suresha P B, Liu C, et al. Combining sparse coding and time-domain features for heart sound classification. Physiol Meas, 2017, 38(8): 1701-1713.
15. Chen Lingguang, Wu F S, Xu Yong,, et al. Blind separation of heart sounds. Journal of the Acoustical Society of America, 2017, 137(04): 2388-2388.
16. 许春冬, 周静, 龙清华, 等. 基于coif-5小波的心音自适应阈值降噪方法. 科学技术与工程, 2019, 19(2): 106-113.
17. Yuan Wenhao, Lin Jiajun, Wei A N, et al. Noise estimation based on time–frequency correlation for speech enhancement. Applied Acoustics, 2013, 74(5): 770-781.
18. Hirszhorn A, Dov D, Talmon R, et al. Transient interference suppression in speech signals based on the OM-LSA algorithm//International Workshop on Acoustic Signal Enhancement, Aachen: VDE, 2012: 1-4.
19. 袁文浩, 林家骏, 王雨, 等. 一种基于噪声分类的语音增强方法. 华东理工大学学报:自然科学版, 2014, 40(2): 196-201.
20. 曹克宇. 语音系统中瞬态噪声抑制算法的研究. 哈尔滨: 哈尔滨工业大学, 2017.
21. 陈成斌. 针对于家居环境的语音增强系统的研究与开发. 广州: 华南理工大学, 2015.
22. 刘凤增. 复杂环境下语音增强方法研究. 长沙: 国防科学技术大学, 2011.
23. 李国正, 谭南林, 苏树强, 等. 混沌同步系统降噪方法及其在滚动轴承故障诊断中的应用. 北京理工大学学报, 2019, 39(7): 669-675.
24. Cohen I, Berdugo B. Speech enhancement for non-stationary noise environments. Signal Processing, 2001, 81(11): 2403-2418.
25. Cohen I, Berdugo B. Spectral enhancement by tracking speech presence probability in subbands//IEEE Workshop on Hands-Free Speech Communication, Kyoto: IEEE, 2001: 95-98.
26. Tran T D, Nguyen Q C, Nguyen D K. Speech enhancement using modified IMCRA and OMLSA methods//International Conference on Communications and Electronics 2010, Nha Trang: IEEE, 2010: 195-200.
27. Ephraim H, Malah D. Speech enhancement using a minimum mean square error short-time spectral amplitude estimator. IEEE Transactions on Acoustics, Speech and Signal Processing, 1984, 32(06): 1109-1121.
28. Hou Xuchu, Guo S, Cui H, et al. Speech enhancement for Non-Stationary noise environments//2009 International Conference on Information Engineering and Computer Science, Wuhan: IEEE, 2009: 1-3.
29. Cohen I. Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging. IEEE Transactions on Speech and Audio Processing, 2003, 11(5): 466-475.
30. 熊晶. 语音增强中噪声估计的研究. 兰州: 兰州交通大学, 2015.
31. Clifford G, Liu Chengyu, Moody B, et al. Classification of normal/abnormal heart sound recordings: the PhysioNet/computing in cardiology challenge 2016//2016 Computing in Cardiology Conference (CinC), 2016: 609-612.
32. Liu C Y, Springer D, Li Q, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas, 2016, 37(12): 2181-2213.
33. 成谢锋, 陈亚敏. S1和S2共振峰频率在心音分类识别中的应用. 南京邮电大学学报:自然科学版, 2017, 37(5): 7-12.
34. 陈亚敏. 一种基于级联无损声管的心音产生模型的研究及应用. 南京: 南京邮电大学, 2017.
35. Hong Tang, Chen Huaming, Li Ting, et al. Classification of normal/abnormal heart sound recordings based on multi-domain features and back propagation neural network//2016 Computing in Cardiology Conference (CinC), Vancouver: IEEE, 2016: 593-596.
36. Springer D B, Tarassenko L, Clifford G D. Logistic Regression-HSMM-Based heart sound segmentation. IEEE Trans Biomed Eng, 2016, 63(4): 822-832.
37. Bouril A, Aleinikava D, Guillem M S, et al. Automated classification of normal and abnormal heart sounds using support vector machines//2016 Computing in Cardiology Conference (CinC), Vancouver: IEEE, 2016: 549-552.

Previous Article
Segmentation of heart sound signals based on duration hidden Markov model
Next Article
Simulation research on magnetoacoustic B-scan imaging of magnetic nanoparticles

Journal of Biomedical Engineering

Heart sound denoising by dynamic noise estimation

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content