{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:39:14Z","timestamp":1774449554834,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST CREST VoicePersonae Project","award":["JPMJCR18A6"],"award-info":[{"award-number":["JPMJCR18A6"]}]},{"name":"MEXT KAKENHI","award":["16H06302"],"award-info":[{"award-number":["16H06302"]}]},{"name":"MEXT KAKENHI","award":["17H04687"],"award-info":[{"award-number":["17H04687"]}]},{"name":"MEXT KAKENHI","award":["18H04120"],"award-info":[{"award-number":["18H04120"]}]},{"name":"MEXT KAKENHI","award":["18H04112"],"award-info":[{"award-number":["18H04112"]}]},{"name":"MEXT KAKENHI","award":["18KT0051"],"award-info":[{"award-number":["18KT0051"]}]},{"name":"MEXT KAKENHI","award":["19K24372"],"award-info":[{"award-number":["19K24372"]}]},{"name":"SOKENDAI"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3111566","type":"journal-article","created":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T21:13:06Z","timestamp":1631567586000},"page":"3000-3011","source":"Crossref","is-referenced-by-count":13,"title":["Multi-Metric Optimization Using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9058-633X","authenticated-orcid":false,"given":"Haoyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref38","first-page":"1256","article-title":"Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation","volume":"27","author":"luo","year":"0","journal-title":"IEEE Transactions on Audio"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2017.2704421"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.06.002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref36","article-title":"End-to-end multi-task denoising for joint SDR and PESQ optimization","author":"kim","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054578"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.06.001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2856374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.2166600"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2774250"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.05.001"},{"key":"ref26","first-page":"2031","article-title":"Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"2019","journal-title":"Proc Int Conf Mach Learn PMLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1090.001.0001"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1121\/1.4807563"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1121\/1.5129050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2748"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"3552","DOI":"10.21437\/Interspeech.2013-764","article-title":"Intelligibility-enhancing speech modifications: The hurricane challenge","author":"cooke","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref40","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1641"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.04.007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-400"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1404.677"},{"key":"ref17","first-page":"1043","article-title":"Mel-generalized cepstral analysis - A unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref18","first-page":"57","article-title":"A log domain pulse model for parametric speech synthesis","volume":"26","author":"degottex","year":"0","journal-title":"IEEE Transactions on Audio"},{"key":"ref19","author":"institute","year":"0","journal-title":"American National Standard Methods for Calculation of the Speech Intelligibility Index"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472704"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-285"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2240297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2409780"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-197"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6954309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.10.003"},{"key":"ref46","article-title":"HARVARD speech corpus - Audio recording 2019","author":"demonte","year":"0"},{"key":"ref45","article-title":"Hurricane natural speech corpus - higher quality version","author":"valentini-botinhao","year":"0"},{"key":"ref48","article-title":"Voicebox: Speech processing toolbox for MATLAB","author":"brookes","year":"0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3087"},{"key":"ref42","article-title":"Network in network","author":"lin","year":"2013"},{"key":"ref41","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"xu","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162058"},{"key":"ref43","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09536406.pdf?arnumber=9536406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T08:37:15Z","timestamp":1725784635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9536406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3111566","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}