{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:02:14Z","timestamp":1780765334421,"version":"3.54.1"},"reference-count":41,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,9,1]]},"DOI":"10.1587\/transinf.2021edp7103","type":"journal-article","created":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T22:22:47Z","timestamp":1661984567000},"page":"1568-1580","source":"Crossref","is-referenced-by-count":5,"title":["Highly-Accurate and Real-Time Speech Measurement for Laser Doppler Vibrometers"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Yahui","family":"WANG","sequence":"first","affiliation":[{"name":"School of Cyberspace Security, Beijing University of Posts and Telecommunications"},{"name":"Key Laboratory of Computational Optical Imaging Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxi","family":"ZHANG","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Optical Imaging Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"WU","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Optical Imaging Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxin","family":"KONG","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Optical Imaging Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbiao","family":"WANG","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Optical Imaging Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxin","family":"ZHANG","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Beijing University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] T. Lv, X. Han, S. Wu, and Y. Li, \u201cThe effect of speckles noise on the Laser Doppler Vibrometry for remote speech detection,\u201d Optics Communications, vol.440, pp.117-125, 2019. 10.1016\/j.optcom.2019.02.014","DOI":"10.1016\/j.optcom.2019.02.014"},{"key":"2","unstructured":"[2] M. Johansmann, G. Siegmund, M. Pineda, \u201cTargeting the limits of laser doppler vibrometry,\u201d Proc. IDEMA, pp.1-12, 2005."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] S. Sami, Y. Dai, S.R. Tan, N. Roy, J. Han, \u201cSpying with your robot vacuum cleaner: eavesdropping via lidar sensors,\u201d 18th ACM Conf. Embedded Networked Sensor Systems, pp.354-367, ACM, Nov. 2020. 10.1145\/3384419.3430781","DOI":"10.1145\/3384419.3430781"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] M.T. Wang, Y. Zhu, and Y.N. Mu, \u201cA two-stage amplifier of laser eavesdropping model based on waveguide fiber taper,\u201d Defence Technology, vol.15, no.1, pp.95-97, Feb. 2019. 10.1016\/j.dt.2018.07.001","DOI":"10.1016\/j.dt.2018.07.001"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] S. Peng, T. Lv, X. Han, S. Wu, C. Yan, and H. Zhang, \u201cRemote speaker recognition based on the enhanced LDV-captured speech,\u201d Applied Acoustics, vol.143, pp.165-170, Jan. 2019. 10.1016\/j.apacoust.2018.08.007","DOI":"10.1016\/j.apacoust.2018.08.007"},{"key":"6","unstructured":"[6] T. Sugawara, B. Cyr, S. Rampazzi, D. Genkin, and K. Fu, \u201cLight commands: Laser-based audio injection attacks on voice-controllable systems,\u201d Proc. 29th USENIX Conference on Security Symposium, pp.2631-2648, Aug. 2020."},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] J. Zhou, X. Yu, and X. Long, \u201cCombined dual-beam and reference beam LDV for vehicle inertial navigation system,\u201d Optik-International Journal for Light and Electron Optics, vol.123, no.15, pp.1346-1351, Aug. 2012. 10.1016\/j.ijleo.2011.09.005","DOI":"10.1016\/j.ijleo.2011.09.005"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] P. Phua B, Y. Fu, M. Guo, and H. Liu, \u201cMulti-beam Laser Doppler vibrometer with fiber sensing head,\u201d American Institute of Physics Conference Series, vol.1457, no.1, pp.219-226, June 2012. 10.1063\/1.4730560","DOI":"10.1063\/1.4730560"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] V. Aranchuk, I. Aranchuk, B. Carpenter, and C.J. Hickey, \u201cLaser Doppler multi-beam differential vibrometry,\u201d J. Acoustical Society of America, vol.148, no.4, pp.2533-2533, Dec. 2020. 10.1121\/1.5147034","DOI":"10.1121\/1.5147034"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] V. Srinivasarao and U. Ghanekar, \u201cSpeech intelligibility enhancement: a hybrid wiener approach,\u201d Int. J. Speech Technology, vol.23, pp.517-525, 2020. 10.1007\/s10772-020-09737-4","DOI":"10.1007\/s10772-020-09737-4"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] G.E. Spoorthi, S. Gorthi, and R.K.S. S. Gorthi, \u201cPhaseNet: A deep convolutional neural network for two-dimensional phase unwrapping,\u201d IEEE Signal Process. Lett., vol.26, no.1, pp.54-58, Jan. 2018. 10.1109\/LSP.2018.2879184","DOI":"10.1109\/LSP.2018.2879184"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] G.E. Spoorthi, R.K.S.S. Gorthi, and S. Gorthi, \u201cPhaseNet 2.0: Phase unwrapping of noisy data based on deep learning approach,\u201d IEEE Trans. Image Process., vol.29, pp.4862-4872, 2020. 10.1109\/TIP.2020.2977213","DOI":"10.1109\/TIP.2020.2977213"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] L. Zhou, H. Yu, and Y. Lan, \u201cDeep convolutional neural network-based robust phase gradient estimation for two-dimensional phase unwrapping using SAR interferograms,\u201d IEEE Trans. Geosci. Remote Sens., vol.58, no.7, pp.4653-4665, July 2020. 10.1109\/TGRS.2020.2965918","DOI":"10.1109\/TGRS.2020.2965918"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] I. Herszterg, M. Poggi, and T. Vidal, \u201cTwo-dimensional phase unwrapping via balanced spanning forests,\u201d Informs J. Computing, vol.31, no.3, pp.527-543, 2019. 10.1287\/ijoc.2018.0832","DOI":"10.1287\/ijoc.2018.0832"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] W. Yin, C. Zuo, S. Feng, T. Tao, Y. Hu, L. Huang, J. Ma, and Q. Chen, \u201cHigh-speed three-dimensional shape measurement using geometry-constraint-based number-theoretical phase unwrapping,\u201d Optics and Lasers in Engineering, vol.115, pp.21-31, April 2019. 10.1016\/j.optlaseng.2018.11.006","DOI":"10.1016\/j.optlaseng.2018.11.006"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] R.M. Goldstein, H.A. Zebker, and C.L. Werner, \u201cSatellite radar interferometry: Two-dimensional phase unwrapping,\u201d Radio Science, vol.23, no.4, pp.713-720, 2016. 10.1029\/RS023i004p00713","DOI":"10.1029\/RS023i004p00713"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] W. Xu and I. Cumming, \u201cA region-growing algorithm for InSAR phase unwrapping,\u201d IEEE Trans. Geosci. Remote Sens., vol.37, no.1, pp.1-124, Jan. 1999. 10.1109\/36.739143","DOI":"10.1109\/36.739143"},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] J. Qi, J. Du, S.M. Siniscalchi, and C.H. Lee, \u201cA theory on deep neural network based vector-to-vector regression with an illustration of its expressive power in speech enhancement,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.27, no.12, pp.1932-1943, Dec. 2019. 10.1109\/TASLP.2019.2935891","DOI":"10.1109\/TASLP.2019.2935891"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Y. Li, T. Jiang, and S. Qin, \u201cMulti-scale generative adversarial networks for speech enhancement,\u201d 2019 IEEE Global Conf. Signal and Information Processing (GlobalSIP), 2020. 10.1109\/GlobalSIP45357.2019.8969193","DOI":"10.1109\/GlobalSIP45357.2019.8969193"},{"key":"20","unstructured":"[20] T. Bai, J. Wu, M. Li, et al., \u201cApplication of DRNN in the sound measurement system of laser Doppler vibrometer,\u201d Laser Technology, vol.43, no.1, pp.113-118, 2019."},{"key":"21","unstructured":"[21] Y.M. Tian, H.Q. Chen, and W.F. Zeng, \u201cApplication of laser detector system based on improving algorithm in speech enhancement,\u201d J. Optoelectronics Laser, vol.18, no.12, pp.1489-1491, 2007."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] M. Bachute and R.D. Kharadkar, \u201cAnalysis of least mean square and recursive least squared adaptive filter algorithm for speech enhancement application,\u201d Smart and Innovative Trends in Next Generation Computing Technologies, pp.590-604Singapore, Springer, 2018. 10.1007\/978-981-10-8657-1_45","DOI":"10.1007\/978-981-10-8657-1_45"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y. Avargel and I. Cohen, \u201cSpeech measurements using a laser Doppler vibrometer sensor: Application to speech enhancement,\u201d 2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), IEEE, 2011. 10.1109\/HSCMA.2011.5942375","DOI":"10.1109\/HSCMA.2011.5942375"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] I. Cohen and B. Berdugo, \u201cSpeech enhancement for non-stationary noise environments,\u201d Signal Processing, vol.81, no.11, pp.2403-2418, Nov. 2001. 10.1016\/S0165-1684(01)00128-1","DOI":"10.1016\/S0165-1684(01)00128-1"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] H.Y. Zhang, T. Lv, and C. Yan, \u201cThe novel role of arctangent phase algorithm and voice enhancement techniques in laser hearing,\u201d Applied Acoustics, vol.126, pp.136-142, Nov. 2017. 10.1016\/j.apacoust.2017.05.024","DOI":"10.1016\/j.apacoust.2017.05.024"},{"key":"26","unstructured":"[26] C. Lacombe, P. Kornprobst, G. Aubert, L. Blanc-Feraud, \u201cA variational approach to one dimensional phase unwrapping,\u201d 16th Int. Conf. Pattern Recognit., 2002. 10.1109\/ICPR.2002.1048426"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] H. Takajo and T. Takahashi, \u201cLeast-squares phase estimation from the phase difference,\u201d J. Opt. Soc. Am. A, vol.5, no.3, pp.1818-1827, 1988. 10.1364\/JOSAA.5.000416","DOI":"10.1364\/JOSAA.5.000416"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] M. Costantini, \u201cA novel phase unwrapping method based on network programming,\u201d IEEE Trans. Geosci. Remote Sens., vol.36, no.3, pp.813-813, May 1998. 10.1109\/36.673674","DOI":"10.1109\/36.673674"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] S.V. Vaseghi, \u201cLinear prediction models,\u201d Advanced Digital Signal Processing and Noise Reduction, pp.185-213, 1996. 10.1002\/9780470740156.ch8","DOI":"10.1007\/978-3-322-92773-6_7"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] V. Mahalingam, M. Kesheorey, and N. Sitaram, \u201cOn a real time implementation of LPC speech coder on a bit-slice microprocessor based digital signal processor,\u201d IETE J. Research, vol.34, no.2, pp.143-146, 1988. 10.1080\/03772063.1988.11436719","DOI":"10.1080\/03772063.1988.11436719"},{"key":"31","unstructured":"[31] S. Kwong and K.F. Man, \u201cA speech coding algorithm based on predictive coding,\u201d Proc. DCC '95. Data Compression Conference, 1995. 10.1109\/DCC.1995.515565"},{"key":"32","unstructured":"[32] L. Tao, Research on Long-distance Laser Coherent Speech Signal Detection Technology, University of Chinese Academy of Sciences (Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences), 2019."},{"key":"33","doi-asserted-by":"publisher","unstructured":"[33] J. Vass, R. \u0160m\u00edd, R.B. Randall, P. Sovka, C. Cristalli, and B. Torcianti, \u201cAvoidance of speckle noise in laser vibrometry by the use of kurtosis ratio: Application to mechanical fault diagnostics, Mechanical Systems and Signal Processing, vol.22, no.3, pp.647-671, April 2008. 10.1016\/j.ymssp.2007.08.008","DOI":"10.1016\/j.ymssp.2007.08.008"},{"key":"34","doi-asserted-by":"publisher","unstructured":"[34] G.N. Boshnakov and S. Lambert-Lacroix, \u201cA periodic Levinson-Durbin algorithm for entropy maximization, Computational Statistics and Data Analysis, vol.56, no.1, pp.15-24, Jan. 2012. 10.1016\/j.csda.2011.07.001","DOI":"10.1016\/j.csda.2011.07.001"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] S.V. Vaseghi, \u201cImpulsive noise,\u201d Advanced Digital Signal Processing and Noise Reduction, 4th ed. Media Pte Ltd., Singapore, 2008. 10.1002\/9780470740156","DOI":"10.1002\/9780470740156"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] S. Boll, \u201cSuppression of acoustic noise in speech using spectral subtraction,\u201d IEEE Trans. Acoust., Speech, Signal Process., vol.27, no.2, pp.113-120, April 1979. 10.1109\/TASSP.1979.1163209","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"37","doi-asserted-by":"publisher","unstructured":"[37] H. Gustafsson, S.E. Nordholm, and I. Claesson, \u201cSpectral subtraction using reduced delay convolution and adaptive averaging,\u201d IEEE Trans. Speech Audio Process., vol.9, no.8, pp.799-807, Nov. 2001. 10.1109\/89.966083","DOI":"10.1109\/89.966083"},{"key":"38","unstructured":"[38] D. Timit, Acoustic-Phonetic Speech Database, National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA, CD-ROM, 1993."},{"key":"39","doi-asserted-by":"publisher","unstructured":"[39] R.E. Crochiere, J.M. Tribolet, and L.R. Rabiner, \u201cAn interpretation of the log likelihood ratio as a measure of waveform coder performance,\u201d IEEE Trans. Acoust., Speech, Signal Process., vol.28, no.3, pp.318-323, June 1980. 10.1109\/TASSP.1980.1163417","DOI":"10.1109\/TASSP.1980.1163417"},{"key":"40","unstructured":"[40] S. Quackenbush, T. Barnwell, and M. Clements, Objective measures of speech quality, Prentice-Hall, NJ, 1988."},{"key":"41","unstructured":"[41] ITU, \u201cPerceptual evaluation of speech quality (PESQ), an objective method for end-to-end speech quality assessment of narrowband telephone networks and speech coders,\u201d ITU-T Recommendation, p.862, 2001."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/9\/E105.D_2021EDP7103\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T04:55:57Z","timestamp":1715230557000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/9\/E105.D_2021EDP7103\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":41,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7103","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,1]]},"article-number":"2021EDP7103"}}