{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T19:05:08Z","timestamp":1792868708006,"version":"4.5.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62171427"],"award-info":[{"award-number":["62171427"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024]]},"DOI":"10.1109\/taslp.2024.3393732","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:56:58Z","timestamp":1714067818000},"page":"2508-2521","source":"Crossref","is-referenced-by-count":10,"title":["Optimizing Audio-Visual Speech Enhancement Using Multi-Level Distortion Measures for Audio-Visual Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0904-8946","authenticated-orcid":false,"given":"Hang","family":"Chen","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-3920","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-6647","authenticated-orcid":false,"given":"Bao-Cai","family":"Yin","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-1744","authenticated-orcid":false,"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/TASSP.1984.1164453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-552"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842156"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-853"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683648"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036783"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2953810"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746398"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607895"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2008.00615.x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4324\/9781315808253"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1995-381"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.1358887"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638354"},{"key":"ref30","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fisher III","year":"2001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SAM.2002.1191001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745030"},{"key":"ref33","first-page":"1173","article-title":"Audio-visual sound separation via hidden Markov models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hershey","year":"2001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1955"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP45357.2019.8969244"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928140"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref52","first-page":"2891","article-title":"Addressing the loss-metric mismatch with adaptive loss alignment","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045180"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918403"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518541"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461965"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-582"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(82)90112-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096807"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094773"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10483"},{"key":"ref72","doi-asserted-by":"crossref","DOI":"10.4135\/9781412983808","volume-title":"Correlation: Parametric and Nonparametric Measures","author":"Chen","year":"2002"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883254"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2358871"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/BF02060937"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref78","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10508446.pdf?arnumber=10508446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T04:43:33Z","timestamp":1715057013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3393732","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}