Application of DRNN in voice measurement system of laser Doppler vibrometer

BAI Tao; WU Jin; LI Minglei; WAN Lei; LI Danyang

doi:10.7510/jgjs.issn.1001-3806.2019.01.022

LASER TECHNOLOGY > 2019 > 43(1): 109-114. > DOI: 10.7510/jgjs.issn.1001-3806.2019.01.022

BAI Tao, WU Jin, LI Minglei, WAN Lei, LI Danyang. Application of DRNN in voice measurement system of laser Doppler vibrometer[J]. LASER TECHNOLOGY, 2019, 43(1): 109-114. DOI: 10.7510/jgjs.issn.1001-3806.2019.01.022

Citation:

PDF (6853 KB)

Application of DRNN in voice measurement system of laser Doppler vibrometer

BAI Tao^1,2,
WU Jin^1, ,,
LI Minglei^1,2,
WAN Lei^1,2,
LI Danyang^1,2

1.
Institue of Electronics, Chinese Academy of Sciences, Beijing 100190, China
2.
Graduate University of Chinese Academy of Sciences, Beijing 100040, China

More Information

Received Date: March 14, 2018
Revised Date: April 12, 2018
Published Date: January 24, 2019

Graphical Abstract

Abstract

Abstract

In order to reduce the noise introduced to speech signal by a laser Doppler vibrometer during the measurement of sound, the method of deep recurrent neural network(DRNN) speech signal denoising was adopted. The speech signal collected from laser Doppler measurement system was denoised. By using the deep recurrent neural network with 1 layer~3 layers and 1024 neurons per layer, the speech signals with signal-to-noise ratio from -6dB to 6dB were processed. After theoretical analysis and experimental verification, the results show that, as the number of layers increases, the quality of speech signals has risen to 8dB~12dB in many evaluation indexes. DRNN can effectively denoise the speech signals collected by laser Doppler acoustic system. The research is of practical significance for improving the quality of speech signals.
- laser technique,
- laser Doppler vibrometer,
- speech signal denoising,
- deep recurrent neural network

FullText(HTML)

References (19)

References

[1]	LI F F, WU J, ZHAO Zh L, et al. Air coupled vibration detection of all-fiber laser Doppler vibrometer[J]. High Power Laser and Particle Beams, 2012, 24(11): 2549-2554(in Chinese). DOI: 10.3788/HPLPB
[2]	YU G, WANG Sh G, YU J H. Technology of digital speckle pattern interferometry and its applications[J]. Laser Technology, 2002, 26(3): 237-240(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jgjs200203006
[3]	JING X J. Research and implementation of speech enhancement algorithm[D]. Hangzhou: Zhejiang University, 2005: 1-55(in Chinese).
[4]	YUE D G, XIE Zh W. A new method to evaluate nonlinear distortion[J]. Technical Acoustics, 2007, 26(1): 84-89(in Chinese). http://ieeexplore.ieee.org/document/4263750/
[5]	XU Y, DU J, DAI L R, et al. A regression approach to speech enhancement based on deep neural networks[J]. IEEE-ACM Transactions on Audio Speech and Language Processing, 2013, 23(1): 7-19. http://ieeexplore.ieee.org/document/6932438/
[6]	HUANG P S, MIN J K, MARK H J, et al. Joint optimization of masks and deep recurrent neural networks for monaural source separation[J]. IEEE-ACM Transactions on Audio Speech and Language Processing, 2015, 23(12): 2136-2147. DOI: 10.1109/TASLP.2015.2468583
[7]	HAN W, ZHANG X W, ZHOU X Y, et al. Joint optimization of deep neural networks and constrained Wiener filter for single channel speech enhancement[J]. Application Research of Computers, 2017, 34(3): 706-713(in Chinese).
[8]	YAO Y, WANG Q J, ZHOU W, et al. Research on speech enhancement based on spectral subtraction and neural network[J]. Electronic Measurement Technology, 2017, 40(7): 74-79(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTOTAL-DZCL201707017.htm
[9]	LI W H, LIU M, ZHU Z G, et al. LDV remote voice acquisition and enhancement[J]. International Conference on Pattern Recognition, 2006, 20(24): 262-265. http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC027012733/
[10]	LV T, ZHANG H Y, GUO J, et al. Acquisition and enhancement of remote voice based on laser coherent method[J]. Optics and Precision Engineering, 2017, 25(3): 569-575(in Chinese). DOI: 10.3788/OPE.
[11]	QU Zh, ZHANG B H. An improved wavelet threshold algorithm applied in laser interception[J]. Laser Technology, 2014, 38(2): 218-224(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTotal-JGJS201402016.htm
[12]	XU Y. Research on deep neural network based speech enhancement[D]. Hefei: University of Science and Technology of China, 2015: 55-75(in Chinese).
[13]	CHENG Y P, BU F L. Experiment study on phase perception in speech[J]. Acta Acustica, 2003, 28(1): 7-11(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1177/001312457701000105
[14]	HERMANS M, SCHRAUWEN B. Training and analyzing deep recurrent neural networks[R]. Lake Tahoe, USA: Proceedings of International Conference on Learning Representations(NIPS), 2013: 190-198.
[15]	WERBOS P J. Backpropagation through time: what it does and how to do it[J]. Proceedings of the IEEE, 1990, 78(10): 1550-1560. DOI: 10.1109/5.58337
[16]	HUO L, ZENG X D, AN Sh Y, et al. Vibration measurement and analysis by means of laser Doppler heterodyne principle[J]. Laser Technology, 2011, 35(5): 600-602(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jgjs201105007
[17]	LIANG N. Research on laser Doppler vibrometer with homodyne detection[D]. Beijing: The University of Chinese Academy of Sciences, 2014: 13-23(in Chinese).
[18]	VINCENT E, GRIBONVAL R, FEVOTTE C. Performance measurement in blind audio source separation[J]. IEEE Trans on Audio Speech & Language Processing, 2006, 14(4):1462-1469. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=318e4293663d87ef4916ef92b4998820
[19]	ZHANG L W, JIA Ch, ZHANG X W, et al. Speech enhancement based on convolutive nonnegative matrix factorization with sparseness constraints[J]. Journal of Data Acquisition and Processing, 2014, 29(2): 259-264(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=sjcjycl201402016

[1]	YAN Xin, YING Kaining, DAI Lunan, TAN Junfu, SHEN Zhonghua, NI Chenyin. Research on laser ultrasonic wavefield based on physical-informed neural network[J]. LASER TECHNOLOGY, 2024, 48(1): 105-113. DOI: 10.7510/jgjs.issn.1001-3806.2024.01.017
[2]	DAI Jinke, ZHENG Suzhen, SU Juan. 3-D surface reconstruction based on structured light and deep neural network[J]. LASER TECHNOLOGY, 2023, 47(6): 831-840. DOI: 10.7510/jgjs.issn.1001-3806.2023.06.015
[3]	GE Yifan, LU Xu, LIU Yuzhu. Research on eggshell via laser-induced breakdown spectroscopy and neural network[J]. LASER TECHNOLOGY, 2022, 46(4): 532-537. DOI: 10.7510/jgjs.issn.1001-3806.2022.04.015
[4]	HUANG Weiwei, YOU Deyong, GAO Xiangdong, ZHANG Yanxi, HUANG Yuhui. Laser welding steady status recognition method based on correlation analysis and neural network[J]. LASER TECHNOLOGY, 2022, 46(3): 312-319. DOI: 10.7510/jgjs.issn.1001-3806.2022.03.004
[5]	GUAN Shihao, YANG Guang, LI Hao, FU Yanyu. Hyperspectral image classification based on 3-D convolutional recurrent neural network[J]. LASER TECHNOLOGY, 2020, 44(4): 485-491. DOI: 10.7510/jgjs.issn.1001-3806.2020.04.015
[6]	XU Da-peng, ZHOU Jian-zhong, GUO Hua-feng, JI Xia. Quality prediction of laser cladding layer based on improved neural network[J]. LASER TECHNOLOGY, 2007, 31(5): 511-514.
[7]	XIA Gui-fen, ZHAO Bao-jun, HAN Yue-qiu. Chaotic weak signal detection in the long range laser rangefinders using neural network[J]. LASER TECHNOLOGY, 2006, 30(5): 449-451.
[8]	WANG Xiu-feng, LÜ Xiao-dong, CHEN Guang-nan, HU Shi-guang. Application of artificial neural network in laser sheet metal bending[J]. LASER TECHNOLOGY, 2005, 29(3): 244-247.
[9]	Mo Changtao, Chen Changzheng, Zhang Lili, Sun Fengjiu. Neural network application in position sensitive detector[J]. LASER TECHNOLOGY, 2003, 27(6): 594-596.
[10]	Wang Da-cheng. Controlling laser surface strengthening process based on artificial neural network[J]. LASER TECHNOLOGY, 2003, 27(4): 317-320.

Cited By

Cited by

Periodical cited type(4)

1.	芮小博，孔欣玥，李磊霞，伍洲，王永彪，王亚慧，徐立鑫，张宇，张文喜. 激光远距离语音探测技术进展. 激光与光电子学进展. 2024(05): 79-88 .
2.	代欣学，范松涛，周燕. 基于ResUnet和TFGAN网络的激光麦克风语音增强方法. 红外与激光工程. 2023(10): 81-91 .
3.	谈渊，甘学辉，张东剑，刘香玉，廖壑. 基于小波去噪的激光多普勒振动信号处理. 激光技术. 2022(01): 129-133 . 本站查看
4.	沈红伟，刚建华. 激光多普勒技术的机电系统运动模式识别. 激光杂志. 2020(11): 115-119 .

Other cited types(6)

Get Citation

PDF

XML

Article views (2) PDF downloads (5) Cited by(10)

Turn off MathJax

Article Contents

Abstract

References

Application of DRNN in voice measurement system of laser Doppler vibrometer

Abstract

References

Related Articles

Cited by

Periodical cited type(4)

Other cited types(6)

Catalog

Links：

Application of DRNN in voice measurement system of laser Doppler vibrometer

Abstract

References

Related Articles

Cited by

Periodical cited type(4)

Other cited types(6)

Catalog

Links：

Export File

Citation

Format

Content