{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:25:17Z","timestamp":1774448717900,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571435"],"award-info":[{"award-number":["61571435"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Project of the State Key Laboratory of Media Convergence and Communication"},{"DOI":"10.13039\/501100015749","name":"Communication University of China","doi-asserted-by":"publisher","award":["SKLMCC2021KF014"],"award-info":[{"award-number":["SKLMCC2021KF014"]}],"id":[{"id":"10.13039\/501100015749","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":[[2022]]},"DOI":"10.1109\/taslp.2022.3184889","type":"journal-article","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T19:43:34Z","timestamp":1655840614000},"page":"2156-2172","source":"Crossref","is-referenced-by-count":21,"title":["Filtering and Refining: A Collaborative-Style Framework for Single-Channel Speech Enhancement"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4094-8448","authenticated-orcid":false,"given":"Andong","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5656-994X","authenticated-orcid":false,"given":"Chengshi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7179-1044","authenticated-orcid":false,"given":"Guochen","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3286-2126","authenticated-orcid":false,"given":"Juanjuan","family":"Cai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4170-0076","authenticated-orcid":false,"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461819"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3079813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.04.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2225617"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854449"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(96)00063-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907713"},{"key":"ref24","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref26","article-title":"Phase-aware speech enhancement with deep complex U-Net","author":"Choi","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/10.0003321"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1137"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870742"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413580"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ECMSM.2017.7945915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref37","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref41","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2995273"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref44","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref51","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74494-8_69"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref58","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref59","volume-title":"Springer Handbook of Speech Processing","author":"Benesty","year":"2007"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref63","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987441"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3125143"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2631"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414852"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1482"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21419"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref76","year":"2007","journal-title":"ITU-T Recommendation P.862.2: Wideband Extension to Recommendation P. 862 for the Assessment of Wideband Telephone Networks and Speech Codecs"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09802706.pdf?arnumber=9802706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:34:25Z","timestamp":1706762065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9802706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3184889","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}