{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T12:40:58Z","timestamp":1720096858830},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T00:00:00Z","timestamp":1477958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1016\/j.specom.2016.08.002","type":"journal-article","created":{"date-parts":[[2016,8,20]],"date-time":"2016-08-20T10:31:13Z","timestamp":1471689073000},"page":"1-14","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["Speech enhancement of instantaneous amplitude and phase for applications in noisy reverberant environments"],"prefix":"10.1016","volume":"84","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Naushin","family":"Nower","sequence":"additional","affiliation":[]},{"given":"Shota","family":"Morita","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6605-2052","authenticated-orcid":false,"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2016.08.002_bib0001","unstructured":"AURORA-2J, 2004. http:\/\/www.slp.cs.tut.ac.jp\/CENSREC\/en\/CENSREC\/AUR-ORA-2J\/."},{"issue":"6","key":"10.1016\/j.specom.2016.08.002_bib0002","doi-asserted-by":"crossref","first-page":"2575","DOI":"10.1121\/1.397751","article-title":"Modulation masking: effects of modulation frequency, depth and phase","volume":"85","author":"Bacon","year":"1989","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.specom.2016.08.002_bib0003","series-title":"Spatial Hearing: The Psychophysics of Human Sound Localization","author":"Blauert","year":"1983"},{"issue":"2","key":"10.1016\/j.specom.2016.08.002_bib0004","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","article-title":"Suppression of acoustic noise in speech using spectral subtraction","volume":"27","author":"Boll","year":"1979","journal-title":"IEEE Trans. Acoust. Speech Signal Process,"},{"key":"10.1016\/j.specom.2016.08.002_bib0005","unstructured":"The HTK Book (version 3.2), 2002. Cambridge University Engineering Department."},{"issue":"1","key":"10.1016\/j.specom.2016.08.002_bib0006","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1121\/1.413112","article-title":"Temporal envelope and fine structure cues for speech intelligibility","volume":"97","author":"Drullman","year":"1995","journal-title":"J. Acoust. Soc. Am."},{"issue":"6","key":"10.1016\/j.specom.2016.08.002_bib0007","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","article-title":"Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator","volume":"32","author":"Ephraim","year":"1984","journal-title":"IEEE Trans. Acoust. Speech Signal Process,"},{"key":"10.1016\/j.specom.2016.08.002_bib0008","unstructured":"http:\/\/www.pscr.gov\/projects\/testing_evaluation\/audio_quality\/mrt_library\/audio_source_files\/."},{"key":"10.1016\/j.specom.2016.08.002_bib0009","series-title":"Proceedings of Interspeech 2006","first-page":"1447","article-title":"Evaluation of objective measures for speech enhancement","author":"Hu","year":"2006"},{"issue":"1","key":"10.1016\/j.specom.2016.08.002_bib0010","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TASL.2007.911054","article-title":"Evaluation of objective quality measures for speech enhancement","volume":"16","author":"Hu","year":"2008","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"13","key":"10.1016\/j.specom.2016.08.002_bib0011","article-title":"Speech enhancement by spectral subtraction method","volume":"96","author":"Kaladharan","year":"2014","journal-title":"Int. J. Comput. Appl."},{"key":"10.1016\/j.specom.2016.08.002_bib0012","series-title":"Proceedings of the ICASSP 2010","first-page":"4206","article-title":"Single-channel source separation using simplified training complex matrix factorization","author":"King","year":"2010"},{"issue":"4","key":"10.1016\/j.specom.2016.08.002_bib0013","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1109\/TASL.2008.2009015","article-title":"Suppression of late reverberation effect on speech signal using long-term multiple-step linear prediction","volume":"17","author":"Kinoshita","year":"2009","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"issue":"1","key":"10.1016\/j.specom.2016.08.002_bib0014","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1109\/TASL.2010.2045180","article-title":"Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions","volume":"19","author":"Loizou","year":"2011","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"10.1016\/j.specom.2016.08.002_bib0015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2009.08.006","article-title":"Temporal contrast normalization and edge-preserved smoothing of temporal modulation structures of speech for robust speech recognition","volume":"52","author":"Lu","year":"2010","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2016.08.002_bib0016","series-title":"Multimedia Tools and Applications","first-page":"187","article-title":"Temporal modulation normalization for robust speech feature extraction and recognition","volume":"52","author":"Lu","year":"2011"},{"key":"10.1016\/j.specom.2016.08.002_bib0017","series-title":"Proceedings of Interspeech 2013","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"Lu","year":"2013"},{"issue":"6","key":"10.1016\/j.specom.2016.08.002_bib0018","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1250\/ast.29.351","article-title":"Comparative evaluation of modulation transfer function based blind restoration of sub-band power envelopes of speech as a front-end processor for automatic speech recognition systems","volume":"29","author":"Lu","year":"2008","journal-title":"Acoust. Sci. Tech."},{"key":"10.1016\/j.specom.2016.08.002_bib0019","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1016\/j.csl.2010.10.002","article-title":"Sub-band temporal modulation envelopes and their normalization for automatic speech recognition in reverberant environments","volume":"25","author":"Lu","year":"2011","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2016.08.002_bib0020","series-title":"Proc. Interspeech 2008","first-page":"387","article-title":"Effect of compressing the dynamic range of the power spectrum in modulation filtering based speech enhancement","author":"Lyons","year":"2008"},{"key":"10.1016\/j.specom.2016.08.002_bib0021","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.specom.2010.10.005","article-title":"SNR loss: A new objective measure for predicting the intelligibility of noise-suppressed speech","volume":"53","author":"Ma","year":"2011","journal-title":"Speech Commun."},{"issue":"4","key":"10.1016\/j.specom.2016.08.002_bib0022","first-page":"822","article-title":"A corpus-based approach to speech enhancement from nonstationary noise","volume":"19","author":"Ming","year":"2011","journal-title":"IEEE Trans. Trans. Acoust. Speech Signal Process."},{"issue":"4","key":"10.1016\/j.specom.2016.08.002_bib0023","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/s10162-008-0143-x","article-title":"The role of temporal fine structure processing in pitch perception, masking, and speech perception for normal-hearing and hearing-impaired people","volume":"9","author":"Moore","year":"2008","journal-title":"J. Assoc. Res. Otolaryngol."},{"key":"10.1016\/j.specom.2016.08.002_bib0024","series-title":"Proceedings of Interspeech 2012","first-page":"1","article-title":"Phase estimation for signal reconstruction in single-channel speech separation","author":"Mowlaee","year":"2012"},{"key":"10.1016\/j.specom.2016.08.002_bib0025","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.specom.2015.02.006","article-title":"Restoration scheme of instantaneous amplitude and phase using Kalman filter with efficient linear prediction for speech enhancement","volume":"70","author":"Nower","year":"2015","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2016.08.002_bib0026","series-title":"Proceedings of Telecommunications Symposium","first-page":"795","article-title":"Spectral subtraction for reverberation reduction applied to automatic speech recognition","author":"Pacheco","year":"2006"},{"issue":"3","key":"10.1016\/j.specom.2016.08.002_bib0027","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.specom.2010.10.004","article-title":"Role of modulation magnitude and phase spectrum towards speech intelligibility","volume":"53","author":"Paliwal","year":"2011","journal-title":"Speech Commun."},{"issue":"1","key":"10.1016\/j.specom.2016.08.002_bib0028","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/89.221363","article-title":"Efficient vector quantization of LPC parameters at 24 bits\/frame","volume":"1","author":"Paliwal","year":"1993","journal-title":"IEEE Trans. Audio, Speech Lang. Process"},{"key":"10.1016\/j.specom.2016.08.002_bib0029","series-title":"The Oxford Handbook of Auditory Science","author":"Plack","year":"2010"},{"key":"10.1016\/j.specom.2016.08.002_bib0030","series-title":"Proceedings of ICASSP 1999","first-page":"29","article-title":"On phase perception in speech","author":"Pobloth","year":"1999"},{"key":"10.1016\/j.specom.2016.08.002_bib0031","series-title":"Proceedings of ICASSP2001","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs","author":"Rix","year":"2001"},{"key":"10.1016\/j.specom.2016.08.002_bib0032","series-title":"Proceedings of ICASSP1984","first-page":"623","article-title":"Speech enhancement based on a prior signal to noise estimation","author":"Scalart","year":"1984"},{"key":"10.1016\/j.specom.2016.08.002_bib0033","first-page":"179","article-title":"Modulation transfer functions: definition and measurement","volume":"49","author":"Schroeder","year":"1981","journal-title":"Acustica"},{"key":"10.1016\/j.specom.2016.08.002_bib0034","series-title":"Sound Material in Living Environment","author":"SMILE","year":"2004"},{"key":"10.1016\/j.specom.2016.08.002_bib0035","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/0167-6393(93)90094-2","article-title":"Assessment for automatic speech recognition: I. comparison of assessment methods","volume":"12","author":"Steeneken","year":"1993","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2016.08.002_bib0036","article-title":"Complex Wavelet Transform","author":"Surhone","year":"2010","journal-title":"Betascript Publishing"},{"key":"10.1016\/j.specom.2016.08.002_bib0037","series-title":"The Role of Envelope and Temporal Fine Structure in the Perception of Noise Degraded Speech","author":"Swaminathan","year":"2010"},{"issue":"5","key":"10.1016\/j.specom.2016.08.002_bib0038","doi-asserted-by":"crossref","first-page":"1747","DOI":"10.1523\/JNEUROSCI.4493-11.2012","article-title":"Psychophysiological analyses demonstrate the importance of neural envelope coding for speech perception in noise","volume":"32","author":"Swaminathan","year":"2012","journal-title":"J. Neurosci."},{"key":"10.1016\/j.specom.2016.08.002_bib0039","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/S0167-6393(98)00077-6","article-title":"A method of signal extraction from noisy signal based on auditory scene analysis","volume":"27","author":"Unoki","year":"1999","journal-title":"Speech Commun."},{"issue":"3","key":"10.1016\/j.specom.2016.08.002_bib0040","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1109\/TSA.2005.858066","article-title":"A two-stage algorithm for one microphone reverberant speech enhancement","volume":"14","author":"Wu","year":"2006","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2016.08.002_bib0041","series-title":"Proceedings of International Conference on Communication Technology","first-page":"1483","article-title":"Modulation analysis for outdoors applications of optical wireless communications","volume":"2","author":"Zhang","year":"2000"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639315300509?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639315300509?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,9,9]],"date-time":"2018-09-09T04:56:49Z","timestamp":1536469009000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639315300509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":41,"alternative-id":["S0167639315300509"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2016.08.002","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2016,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Speech enhancement of instantaneous amplitude and phase for applications in noisy reverberant environments","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2016.08.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2016 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}