{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:09:08Z","timestamp":1784995748119,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["106-2221-E-001-017-MY2"],"award-info":[{"award-number":["106-2221-E-001-017-MY2"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["107-2221-E-001-012-MY2"],"award-info":[{"award-number":["107-2221-E-001-012-MY2"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2976193","type":"journal-article","created":{"date-parts":[[2020,2,26]],"date-time":"2020-02-26T21:31:10Z","timestamp":1582752670000},"page":"1888-1900","source":"Crossref","is-referenced-by-count":45,"title":["Multichannel Speech Enhancement by Raw Waveform-Mapping Using Fully Convolutional Networks"],"prefix":"10.1109","volume":"28","author":[{"given":"Chang-Le","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3487-8212","authenticated-orcid":false,"given":"Sze-Wei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You-Jin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5482-8311","authenticated-orcid":false,"given":"Jen-Wei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0030137"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref71","first-page":"10","article-title":"Phase-controlled sound transfer based on maximally-inconsistent spectrograms","volume":"5","author":"le roux","year":"2011","journal-title":"Signal"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1664"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177943"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/78.790650"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1995.519596"},{"key":"ref31","first-page":"171","article-title":"Multimicrophone noise reduction techniques for hands-free speech recognition-a comparative study","author":"bitzer","year":"1999","journal-title":"Proceeding of Robust Methods for Speech Recognition in Adverse Conditions (ROBUST-99)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.12.008"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/TASSP.1985.1164583","article-title":"Adaptive beamforming for coherent signals and interference","volume":"33","author":"kailath","year":"1985","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"ref34","first-page":"599","article-title":"A dual-microphone speech enhancement algorithm based on the coherence function","volume":"20","author":"yousefian","year":"2012","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2006.270839"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e31803154d0"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1121\/1.4976051"},{"key":"ref63","year":"0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref64","article-title":"Sanlux hmt-11","year":"0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref65","first-page":"504","article-title":"The third ‘chime'speech separation and recognition challenge: Dataset, task and baselines","author":"barker","year":"2015","journal-title":"IEEE Workshop Automatic Speech Recognition Understanding"},{"key":"ref66","article-title":"Csr-i (wsj0) complete","author":"garofalo","year":"2007","journal-title":"Linguistic Data Consortium Philadelphia"},{"key":"ref29","first-page":"3274","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"0","journal-title":"Proc 16th Ann Conf Int Speech Commun Assoc"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842156"},{"key":"ref68","article-title":"Small-footprint keyword spotting on raw audio data with sinc-convolutions","author":"mittermaier","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937212"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.3571422"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1109\/TASLP.2018.2887337","article-title":"Convolutional neural networks to enhance coded speech","volume":"27","author":"zhao","year":"2018","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref20","first-page":"2685","article-title":"Experiments on deep learning for speech denoising","author":"liu","year":"0","journal-title":"Fifteenth Ann Conf Int Speech Commun Assoc"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/72.750549"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref50","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.06.002"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462662"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000537"},{"key":"ref55","author":"zhang","year":"2017","journal-title":"Speech recognition (version 3 8)"},{"key":"ref54","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015"},{"key":"ref53","article-title":"Adversarial audio synthesis","author":"donahue","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TSA.2003.814458","article-title":"A generalized subspace approach for enhancing speech corrupted by colored noise","volume":"11","author":"loizou","year":"2003","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/89.902276"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref12","first-page":"2411","article-title":"Single channel speech enhancement using principal component analysis and mdl subspace selection","author":"vetter","year":"0","journal-title":"Proc Sixth European Conf on Speech Comm and Tech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598306"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495157"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287816"},{"key":"ref17","first-page":"885","article-title":"Ensemble modeling of denoising autoencoder for speech spectrum restoration","author":"lu","year":"0","journal-title":"Fifteenth Ann Conf Int Speech Commun Assoc"},{"key":"ref18","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"2013","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2613960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref5","author":"li","year":"2015","journal-title":"Robust Automatic Speech Recognition A Bridge to Practical Applications"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495147"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553571"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_32"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09013080.pdf?arnumber=9013080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T01:07:33Z","timestamp":1641949653000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9013080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2976193","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}