{"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":1780765334414,"version":"3.54.1"},"reference-count":32,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2023,4,1]]},"DOI":"10.1587\/transfun.2022eap1036","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T22:15:58Z","timestamp":1664489758000},"page":"647-656","source":"Crossref","is-referenced-by-count":1,"title":["Speech Enhancement for Laser Doppler Vibrometer Dealing with Unknown Irradiated Objects"],"prefix":"10.1587","volume":"E106.A","author":[{"given":"Chengkai","family":"CAI","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenta","family":"IWAI","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takanobu","family":"NISHIURA","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] M. Clark, \u201cAn acoustic lens as a directional microphone,\u201d Trans. IRE Prof. Group Audio, vol.AU-2, no.1, pp.5-7, 1954. DOI: 10.1109\/T-SP.1954.28212 10.1109\/t-sp.1954.28212","DOI":"10.1109\/T-SP.1954.28212"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] K.J. Taylor, \u201cAbsolute measurement of acoustic particle velocity,\u201d J. Acoustical Society of America, vol.59, no.3, pp.691-694, 1976. 10.1121\/1.380896","DOI":"10.1121\/1.380896"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] A. Malekjafarian, D. Martinez, and E.J. OBrien, \u201cThe feasibility of using laser Doppler vibrometer measurements from a passing vehicle for bridge damage detection,\u201d Shock and Vibration, vol.2018, no.PT.5, pp.1-10, 2018. 10.1155\/2018\/9385171","DOI":"10.1155\/2018\/9385171"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] D.M. Chen, Y.F. Xu, and W.D. Zhu, \u201cIdentification of damage in plates using full-field measurement with a continuously scanning laser Doppler vibrometer system,\u201d J. Sound and Vibration, vol.422, pp.542-567, 2018. 10.1016\/j.jsv.2018.01.005","DOI":"10.1016\/j.jsv.2018.01.005"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] H. Ayg\u00fcn and A. Apolskis, \u201cThe quality and reliability of the mechanical stethoscopes and laser Doppler vibrometer (LDV) to record tracheal sounds,\u201d Applied Acoustics, vol.161, pp.1-9, 2020. 10.1016\/j.apacoust.2019.107159","DOI":"10.1016\/j.apacoust.2019.107159"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] J.H. Shang, Y. He, D. Liu, H.G. Zang, and W.B. Chen, \u201cLaser Doppler vibrometer for real-time speech-signal acquirement,\u201d Chinese Optics Letters, vol.7, no.8, pp.732-733, 2009. 10.3788\/col20090708.0732","DOI":"10.3788\/COL20090708.0732"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] Q. Lecl\u00e8re and B. Laulagnet, \u201cNearfield acoustic holography using a laser vibrometer and a light membrane,\u201d J. Acoustical Society of America, vol.126, no.3, pp.1245-1249, 2009. 10.1121\/1.3180132","DOI":"10.1121\/1.3180132"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] 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, Edinburgh, UK, pp.109-114, May 2011. DOI: 10.1109\/HSCMA.2011.5942375 10.1109\/hscma.2011.5942375","DOI":"10.1109\/HSCMA.2011.5942375"},{"key":"9","unstructured":"[9] K.H. Li and C.H. Lee, \u201cA deep neural network approach to speech bandwidth expansion,\u201d 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, South Brisbane, QLD, Australia, pp.4395-4399, April 2015. 10.1109\/icassp.2015.7178801"},{"key":"10","unstructured":"[10] T. Lotter and P. Vary, \u201cNoise reduction by joint maximum a posteriori spectral amplitude and phase estimation with super-Gaussian speech modelling,\u201d 12th European Signal Processing Conference, Vienna, Austria, pp.1457-1460, Sept. 2004."},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] M. Krawczyk and T. Gerkmann, \u201cSTFT phase reconstruction in voiced speech for an improved single-channel speech enhancement,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.22, no.12, pp.1931-1940, 2014. 10.1109\/taslp.2014.2354236","DOI":"10.1109\/TASLP.2014.2354236"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] D. Rethage, J. Pons, and X. Serra, \u201cA Wavenet for speech denoising,\u201d 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, AB, Canada, pp.5069-5073, April 2018. 10.1109\/icassp.2018.8462417","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] W.H. Li, M. Liu, Z.G. Zhu, and T.S. Huang, \u201cLDV remote voice acquisition and enhancement,\u201d 18th International Conference on Pattern Recognition, Hong Kong, China, pp.262-265, Aug. 2006. 10.1109\/icpr.2006.746","DOI":"10.1109\/ICPR.2006.746"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] R.H. Peng, B.B. Xu, G.T. Li, C.S. Zheng, and X.D. Li, \u201cLong-range speech acquirement and enhancement with dual-point laser Doppler vibrometers,\u201d IEEE 23rd International Conference on Digital Signal Processing, Shanghai, China, pp.1-5, Nov. 2018. 10.1109\/icdsp.2018.8631671","DOI":"10.1109\/ICDSP.2018.8631671"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Z. Xie, J. Du, I. McLoughlin, Y. Xu, F. Ma, and H. Wang, \u201cDeep neural network for robust speech recognition with auxiliary features from laser-Doppler vibrometer sensor,\u201d 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China, pp.1-5, Oct. 2016. DOI: 10.1109\/ISCSLP.2016.7918400. 10.1109\/iscslp.2016.7918400","DOI":"10.1109\/ISCSLP.2016.7918400"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] T. L\u00fc, J. Guo, H.Y. Zhang, C.H. Yan, and C.J. Wang, \u201cAcquirement and enhancement of remote speech signals,\u201d Optoelectron. Lett., vol.13, no.4, pp.275-278, 2017. 10.1007\/s11801-017-7059-9","DOI":"10.1007\/s11801-017-7059-9"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] S. Boll, \u201cA spectral subtraction algorithm for suppression of acoustic noise in speech,\u201d IEEE International Conference on Acoustics, Speech, and Signal Processing, Washington, DC, USA, vol.4, pp.200-203, April 1979. 10.1109\/icassp.1979.1170696","DOI":"10.1109\/ICASSP.1979.1170696"},{"key":"18","unstructured":"[18] R. Martin, \u201cSpectral subtraction based on minimum statistics,\u201d Proc. EUSIPCO-94, Edinburgh, vol.6, no.8, pp.1182-1185, 1994."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] F. Villavicencio, A. Robel, and X. Rodet, \u201cImproving LPC spectral envelope extraction of voiced speech by true-envelope estimation,\u201d 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, Toulouse, France, vol.1, pp.869-872, May 2006. DOI: 10.1109\/ICASSP.2006.1660159 10.1109\/icassp.2006.1660159","DOI":"10.1109\/ICASSP.2006.1660159"},{"key":"20","unstructured":"[20] H.Y. Gu and S.F. Tsai, \u201cA discrete-cepstrum based spectrum-envelope estimation scheme and its example application of voice transformation,\u201d International Journal of Computational Linguistics, vol.14, no.4, pp.363-382, 2009."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] C. Ledig, L. Theis, F. Husz\u00e1r, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z.H. Wang, and W.Z. Shi, \u201cPhoto-realistic single image super-resolution using a generative adversarial network,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp.4681-4690, July 2017. 10.1109\/cvpr.2017.19","DOI":"10.1109\/CVPR.2017.19"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] D. Griffin and J. Lim, \u201cSignal estimation from modified short-time Fourier transform,\u201d IEEE Trans. Acoust., Speech, Signal Process., vol.32, no.2, pp.236-243, 1984. 10.1109\/tassp.1984.1164317","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] N. Perraudin, P. Balazs, and P.L. S\u00f8ndergaard, \u201cA fast Griffin-Lim algorithm,\u201d 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, USA, pp.1-4, Oct. 2013. 10.1109\/waspaa.2013.6701851","DOI":"10.1109\/WASPAA.2013.6701851"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] S. Takamichi, Y. Saito, N. Takamune, D. Kitamura, and H. Saruwatari, \u201cPhase reconstruction from amplitude spectrograms based on directional-statistics deep neural networks,\u201d Signal Processing, vol.169, p.107368, 2020. 10.1016\/j.sigpro.2019.107368","DOI":"10.1016\/j.sigpro.2019.107368"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. Takamichi, Y. Saito, N. Takamune, D. Kitamura, and H. Saruwatari, \u201cPhase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network,\u201d 16th International Workshop on Acoustic Signal Enhancement, Tokyo, Japan, pp.286-290, Sept. 2018. 10.1109\/iwaenc.2018.8521313","DOI":"10.1109\/IWAENC.2018.8521313"},{"key":"26","unstructured":"[26] K.M. He, X.Y. Zhang, S.Q. Ren, and J. Sun, \u201cDelving deep into rectifiers: Surpassing human-level performance on ImageNet classification,\u201d Proc. IEEE International Conference on Computer Vision, Santiago, Chile, pp.1026-1034, Dec. 2015. 10.1109\/iccv.2015.123"},{"key":"27","unstructured":"[27] Y.N. Dauphin, A. Fan, M. Auli, and D. Grangier, \u201cLanguage modeling with gated convolutional networks,\u201d 16th International Conference on Machine Learning, Ningbo, China, pp.933-941, July 2017."},{"key":"28","unstructured":"[28] J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, and N.L. Dahlgren, \u201cTIMIT acoustic-phonetic continuous speech corpus,\u201d Linguistic Data Consortium, https:\/\/catalog.ldc.upenn.edu\/LDC93S1, 1993."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] P. Wang, Y. Wang, H. Liu, Y. Sheng, X. Wang, and Z. Wei, \u201cSpeech enhancement based on auditory masking properties and log-spectral distance,\u201d Proc. 3rd International Conference on Computer Science and Network Technology, Dalian, China, pp.1060-1064, Oct. 2013. DOI: 10.1109\/ICCSNT.2013.6967286. 10.1109\/iccsnt.2013.6967286","DOI":"10.1109\/ICCSNT.2013.6967286"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] A.W. Rix, J.G. Beerends, M.P. Hollier, and A.P. Hekstra, \u201cPerceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs,\u201d Proc. 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, UT, USA, vol.2, pp.749-752, May 2001. DOI: 10.1109\/ICASSP.2001.941023 10.1109\/icassp.2001.941023","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] C.H. Taal, R.C. Hendriks, R. Heusdens, and J. Jensen, \u201cA short-time objective intelligibility measure for time-frequency weighted noisy speech,\u201d 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, USA, pp.4214-4217, March 2010. DOI: 10.1109\/ICASSP.2010.5495701 10.1109\/icassp.2010.5495701","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] Y. Xu, J. Du, L.R. Dai, and C.H. Lee, \u201cA regression approach to speech enhancement based on deep neural networks,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.23, no.1, pp.7-19, 2014. 10.1109\/taslp.2014.2364452","DOI":"10.1109\/TASLP.2014.2364452"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/4\/E106.A_2022EAP1036\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T23:36:30Z","timestamp":1728084990000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/4\/E106.A_2022EAP1036\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2022eap1036","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,1]]},"article-number":"2022EAP1036"}}