{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T02:36:24Z","timestamp":1768703784477,"version":"3.49.0"},"reference-count":64,"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\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085QF200"],"award-info":[{"award-number":["2308085QF200"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301521"],"award-info":[{"award-number":["62301521"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK2100000033"],"award-info":[{"award-number":["WK2100000033"]}],"id":[{"id":"10.13039\/501100012226","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.2024.3361376","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:50:06Z","timestamp":1706813406000},"page":"1430-1444","source":"Crossref","is-referenced-by-count":11,"title":["Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8074-9553","authenticated-orcid":false,"given":"Rui-Chen","family":"Zheng","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-022X","authenticated-orcid":false,"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-780"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-88"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PERVASIVE.2015.7087096"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.1852873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2096212"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1955"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00197"},{"key":"ref18","article-title":"Towards intelligibility-oriented audio-visual speech enhancement","volume-title":"Proc. Clarity Workshop Mach. Learn. Challenges Hear. Aids","author":"Hussain","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747187"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10041"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2014.05.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113558"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918434"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.4984122"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683564"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.02.002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-23"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/10.0003062"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-939"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1078"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851769"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17693"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096920"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2917039"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987209"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2516"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835719"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682790"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-297"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-429"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383619"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref59","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2108"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10418525.pdf?arnumber=10418525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T21:18:22Z","timestamp":1710364702000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3361376","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}