{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T08:19:10Z","timestamp":1770884350399,"version":"3.50.1"},"reference-count":61,"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":[{"name":"PAII"}],"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.2022.3196168","type":"journal-article","created":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T19:33:13Z","timestamp":1659555193000},"page":"2705-2715","source":"Crossref","is-referenced-by-count":8,"title":["Modeling Speech Structure to Improve T-F Masks for Speech Enhancement and Recognition"],"prefix":"10.1109","volume":"30","author":[{"given":"Suliang","family":"Bu","sequence":"first","affiliation":[{"name":"Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5511-3692","authenticated-orcid":false,"given":"Yunxin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1536-7302","authenticated-orcid":false,"given":"Tuo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"PAII Inc., Palo Alto, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mei","family":"Han","sequence":"additional","affiliation":[{"name":"PAII Inc., Palo Alto, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969547"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.832812"},{"key":"ref3","first-page":"1","article-title":"Microphone array processing for distant speech recognition: Towards real-world deployment","volume-title":"Proc. Asia Pacific Pacific Inf. Process. Assoc. Annu. Summit Conf.","author":"Kumatani","year":"2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2015.7404830"},{"key":"ref5","first-page":"39","article-title":"The RWTH\/UPB\/FORTH system combination for the 4th CHiME challenge evaluation","volume-title":"Proc. 4th IWSPEE","author":"Menne","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref7","first-page":"1","article-title":"Multi-channel speech recognition: LSTMs all the way through","volume-title":"Proc. CHiME-4 Workshop","author":"Erdogan","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898454"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727635"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC.2014.6986284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2016.11.012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2665341"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2427"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495994"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462126"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2440"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521346"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206623"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659692"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55016-4_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.09.003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/1.3179673"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2204978"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/AIMSEC.2011.6009945"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659591"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2209643"},{"key":"ref37","first-page":"9633","article-title":"Listening to sounds of silence for speech denoising","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1859"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362064"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553141"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref47","first-page":"36","article-title":"The USTC-iFlytek system for CHiME-4 challenge","volume-title":"Proc. CHiME-4 Workshop","volume":"4","author":"Du","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-853"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"ref55","volume-title":"Microphone Array Signal Processing","author":"Benesty","year":"2008"},{"key":"ref56","article-title":"Demand: A collection of multi-channel recordings of acoustic noise in diverse environments","volume-title":"Proc. Meetings Acoust.","author":"Thiemann","year":"2013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref58","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref59","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding","author":"Daniel","year":"2011"},{"key":"ref60","first-page":"22","volume-title":"Introduction to Machine Learning","author":"Alpaydm","year":"2004"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2860682"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09849113.pdf?arnumber=9849113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T11:14:17Z","timestamp":1706786057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9849113\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3196168","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}