{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:20:28Z","timestamp":1779294028088,"version":"3.51.4"},"reference-count":105,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["109-2221-E-001-016"],"award-info":[{"award-number":["109-2221-E-001-016"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["109-2634-F-008-006"],"award-info":[{"award-number":["109-2634-F-008-006"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["109-2218-E-011-010"],"award-info":[{"award-number":["109-2218-E-011-010"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003711","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["110-2634-F-002-047"],"award-info":[{"award-number":["110-2634-F-002-047"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Academia Sinica Career Development","award":["AS-CDA-106-M04"],"award-info":[{"award-number":["AS-CDA-106-M04"]}]}],"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.2022.3153265","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T20:31:28Z","timestamp":1645734688000},"page":"1345-1359","source":"Crossref","is-referenced-by-count":34,"title":["Improved Lite Audio-Visual Speech Enhancement"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8824-096X","authenticated-orcid":false,"given":"Shang-Yi","family":"Chuang","sequence":"first","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.Workshops.2007.47"},{"key":"ref2","volume-title":"Robust Automatic Speech Recognition: A Bridge to Practical Applications","author":"Li","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.3571422"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.04.009"},{"issue":"1","key":"ref6","first-page":"111","article-title":"Noise reduction in hearing aids: An overview","volume":"38","author":"Levit","year":"2001","journal-title":"J. Rehabil. Res. Develop."},{"key":"ref7","article-title":"Compression for clinicians, chapter 7","volume-title":"The Many Faces of Compression: Thomson Delmar Learning","author":"Venema","year":"2006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.5093547"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2613960"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_43"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-33213-8","volume-title":"Topics in Acoustic Echo and Noise Control: Selected Methods for the Cancellation of Acoustical Echoes, the Reduction of Background Noise, and Speech Processing","author":"Hnsler","year":"2006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1975.9792"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/78.120793"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/ASP.2005.1110"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045799"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"ref19","first-page":"295","article-title":"Maximum likelihood based noise covariance matrix estimation for multi-microphone speech enhancement","volume-title":"Proc. 20th Eur. Signal Process. Conf.","author":"Kjems","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1976.1170118"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163237"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5.168664"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743782"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/89.902276"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598306"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1381036"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2678458"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287816"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCCE48743.2019.00187"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683047"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053288"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870742"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054001"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054543"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1900"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3008974"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.02.001"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-574"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/72.750549"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2783545"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-409"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3000968"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-13"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.006"},{"key":"ref71","first-page":"7539","article-title":"AV(SE)2: Audio-visual squeeze-excite speech enhancement","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","volume":"2020","author":"Michael"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418840"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP45357.2019.8969244"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2917039"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1617"},{"key":"ref79","article-title":"Training and inference with integers in deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2018"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639508"},{"key":"ref81","first-page":"133","article-title":"Lip synchronization of speech","volume-title":"Audio-Vis. Speech Process., Comput. Cogn. Sci. Approaches","author":"McAllister","year":"1997"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521684"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-201"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682863"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/2141622.2141646"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2250954"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820732"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1955"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref92","volume-title":"IEEE Standard for Binary Floating-Point Arithmetic, Institute of Electrical and Electronics Engineers","year":"1985"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1400"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref96","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33st Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref97","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref98","article-title":"Development of Taiwan Mandarin hearing in noise test","volume-title":"Dept. Speech Lang. Pathol. Audiology, Nat. Taipei Univ. Nurs. Health Sci.","author":"Huang","year":"2005"},{"key":"ref99","article-title":"100 nonspeech environmental sounds","author":"Hu","year":"2004"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/146040"},{"key":"ref101","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/83.841942"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSIT.2010.5563647"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2010.10.002"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09721158.pdf?arnumber=9721158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:08:54Z","timestamp":1705532934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9721158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3153265","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}