{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T18:36:28Z","timestamp":1776364588582,"version":"3.51.2"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2018,2,20]],"date-time":"2018-02-20T00:00:00Z","timestamp":1519084800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1007\/s11042-018-5686-1","type":"journal-article","created":{"date-parts":[[2018,2,20]],"date-time":"2018-02-20T19:38:50Z","timestamp":1519155530000},"page":"18865-18880","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Phase and reverberation aware DNN for distant-talking speech enhancement"],"prefix":"10.1007","volume":"77","author":[{"given":"Zeyan","family":"Oo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khomdet","family":"Phapatanaburi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Iwahashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seiichi","family":"Nakagawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,20]]},"reference":[{"key":"5686_CR1","volume-title":"Speech enhancement","author":"J Benesty","year":"2005","unstructured":"Benesty J, Makino S, Chen J (2005) Speech enhancement. Springer, New York"},{"key":"5686_CR2","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"S Boll","year":"1984","unstructured":"Boll S (1984) Suppression of acoustics noise in speech using spectral subtraction. IEEE Trans on Acoustics, Speech, Signal Processing 32:1109\u20131121","journal-title":"IEEE Trans on Acoustics, Speech, Signal Processing"},{"issue":"2","key":"5686_CR3","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TASSP.1985.1164550","volume":"33","author":"Y Ephraim","year":"1985","unstructured":"Ephraim Y, Malah D (1985) Speech enhancement using a minimum mean square error short-time spectral amplitude estimator. IEEE Trans on Acoustics, Speech and Signal Processing 33(2):443\u2013445","journal-title":"IEEE Trans on Acoustics, Speech and Signal Processing"},{"issue":"4","key":"5686_CR4","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/89.397090","volume":"3","author":"Y Ephraim","year":"1995","unstructured":"Ephraim Y et al (1995) A signal subspace approach for speech enhancement. IEEE Trans on Speech and Audio Processing 3(4):251\u2013266","journal-title":"IEEE Trans on Speech and Audio Processing"},{"issue":"1","key":"5686_CR5","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TASL.2006.876858","volume":"15","author":"RM Hegde","year":"2007","unstructured":"Hegde RM et al (2007) Significance of the Modified Group Delay Feature in Speech Recognition. IEEE Trans on Audio, Speech, and Language Processing 15(1):190\u2013202","journal-title":"IEEE Trans on Audio, Speech, and Language Processing"},{"key":"5686_CR6","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton GE et al (2006) A fast learning algorithm for deep belief Networks. Neural Comput 18:1527\u20131554","journal-title":"Neural Comput"},{"key":"5686_CR7","unstructured":"Kanagasundaram A, Dean D, Sridharan S (2012) JFA based speaker recognition using delta-phase and MFCC features. In: Proc. of SST, pp. 9-12"},{"key":"5686_CR8","doi-asserted-by":"crossref","unstructured":"Kinoshita K, Nakatani T (2011) Speech dereverberation using linear prediction. NTT Technical Review 9(7):1\u20137","DOI":"10.53829\/ntr201107ra3"},{"issue":"4","key":"5686_CR9","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1109\/TASL.2008.2009015","volume":"17","author":"K Kinoshita","year":"2009","unstructured":"Kinoshita K, Delcroix M, Nakatani T, Miyoshi M (2009) Suppression of Late Reverberation Effect on Speech Signal Using Long-Term Multiple\u2013Step Linear Prediction. IEEE trans Audio, Speech and Language Processing 17(4):534\u2013545","journal-title":"IEEE trans Audio, Speech and Language Processing"},{"key":"5686_CR10","doi-asserted-by":"crossref","unstructured":"Kinoshita K et al (2013) The reverb challenge: a common evaluation framework for dereverberation and recognition of reverberant speech. Proc. of IEEE Workshop on Application of Signal Processing to Audio Acoustics","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"5686_CR11","doi-asserted-by":"crossref","unstructured":"Lu X, Tsao Y, Matsuda S, Hori C (2013) Speech enhancement based on deep denoising autoencoder. In: Proc. of Interspeech, pp. 436-440","DOI":"10.21437\/Interspeech.2013-130"},{"key":"5686_CR12","unstructured":"Miao Y et al (2015) Distant aware training for robust speech recognition. Proc. of Interspeech, pp. 761-765"},{"issue":"4","key":"5686_CR13","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1109\/TASL.2011.2172422","volume":"20","author":"S Nakagawa","year":"2012","unstructured":"Nakagawa S et al (2012) Speaker Identification and Verification by Combining MFCC and Phase Information. IEEE Trans on Audio, Speech and Language Processing 20(4):1085\u20131095","journal-title":"IEEE Trans on Audio, Speech and Language Processing"},{"key":"5686_CR14","first-page":"85","volume-title":"Blind speech dereverberation with multi- channel linear prediction based on short time fourier representation","author":"T Nakatani","year":"2008","unstructured":"Nakatani T, Yoshioka T, Kinoshita K, Miyoshi M, Juang BH (2008) Blind speech dereverberation with multi- channel linear prediction based on short time fourier representation. Proc. of ICASSP, Las Vegas, pp 85\u201388"},{"issue":"346","key":"5686_CR15","first-page":"37","volume":"115","author":"Z Oo","year":"2015","unstructured":"Oo Z, Wang L, Masahiro I (2015) Investigation of DNN based Distant-Talking Speech Enhancement. Proc of 109th Spoken Language Research Workshop of IEICE 115(346):37\u201342","journal-title":"Proc of 109th Spoken Language Research Workshop of IEICE"},{"key":"5686_CR16","first-page":"81","volume-title":"WSJCAM0: a british english speech corpus for large vocabulary continuous speech recognition","author":"T Robinson","year":"1995","unstructured":"Robinson T, Fransen J, Pye D, Foote J, Renals S (1995) WSJCAM0: a british english speech corpus for large vocabulary continuous speech recognition. Proc. of ICASSP, Detroit, pp 81\u201384"},{"key":"5686_CR17","first-page":"7398","volume-title":"An investigation of deep neural networks for noise robust speech recognition","author":"ML Seltzer","year":"2013","unstructured":"Seltzer ML, Wang Y (2013) An investigation of deep neural networks for noise robust speech recognition. Proc. of ICASSP, Vancouver, pp 7398\u20137402"},{"issue":"3","key":"5686_CR18","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/TSA.2003.811542","volume":"11","author":"J Tchorz","year":"2003","unstructured":"Tchorz J, Kollmeier B (2003) SNR estimation based on amplitude modulation analysis with applications to noise suppression. IEEE Trans on Speech Audio Process 11(3):184\u2013192","journal-title":"IEEE Trans on Speech Audio Process"},{"issue":"92","key":"5686_CR19","first-page":"1","volume":"2015","author":"Y Ueda","year":"2015","unstructured":"Ueda Y, Wang L, Kai A, Ren B (2015) Environmental dependent denoising autoencoder for distant talking speech recognition. Eurasip Journal on Advances in Signal Processing 2015(92):1\u201311","journal-title":"Eurasip Journal on Advances in Signal Processing"},{"key":"5686_CR20","volume-title":"Handbook of neural network for speech processing","author":"EA Wan","year":"1998","unstructured":"Wan EA, Nelson T (1998) Handbook of neural network for speech processing. Artech House, Boston"},{"key":"5686_CR21","doi-asserted-by":"crossref","unstructured":"Wang L et al (2010) Speaker recognition by combining MFCC and phase information in noisy conditions. IEICE Trans Inf Syst E93-D 9:2397\u20132406","DOI":"10.1587\/transinf.E93.D.2397"},{"key":"5686_CR22","unstructured":"Wang L et al (2015) Relative phase information for detection human speech and spoofed speech. In: Proc. of Interspeech, pp. 2092-2096"},{"key":"5686_CR23","unstructured":"Xiao X et al (2014) The NTU\u2013ADSC system for reverberation challenge 2014. Proc of Reverb Workshop"},{"issue":"4","key":"5686_CR24","first-page":"1","volume":"2016","author":"X Xiao","year":"2016","unstructured":"Xiao X et al (2016) Speech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation. EURASIP Journal of Advances in Signal Processing 2016(4):1\u201318","journal-title":"EURASIP Journal of Advances in Signal Processing"},{"issue":"1","key":"5686_CR25","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Xu Y, Du J, Dai L, Lee C (2014) An Experimental Study on Speech on Deep Neural Networks. IEEE Signal Processing Letter 21(1):65\u201368","journal-title":"IEEE Signal Processing Letter"},{"key":"5686_CR26","doi-asserted-by":"crossref","unstructured":"Xu Y, Du J, Dai L, Lee C (2014) Dynamic noise aware training for speech enhancement based on deep neural networks. Proc. of Interspeech, pp. 2670\u20132674","DOI":"10.21437\/Interspeech.2014-571"},{"key":"5686_CR27","first-page":"7","volume":"23","author":"Y Xu","year":"2015","unstructured":"Xu Y, Du J, Dai L, Lee C (2015) \u201cA Regression Approach to Speech Enhancement Based on Deep Neural Networks\u201d IEEE Trans on Audio. Speech and Language Processing 23:7\u201319","journal-title":"Speech and Language Processing"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-5686-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5686-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5686-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:47:28Z","timestamp":1751410048000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-5686-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,20]]},"references-count":27,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["5686"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-5686-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,20]]},"assertion":[{"value":"23 October 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}