{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T20:03:01Z","timestamp":1768075381972,"version":"3.49.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62306029"],"award-info":[{"award-number":["62306029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation","award":["L233032"],"award-info":[{"award-number":["L233032"]}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","award":["K00120240007"],"award-info":[{"award-number":["K00120240007"]}],"id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091302006"],"award-info":[{"award-number":["ZDSYS20230626091302006"]}]},{"name":"Program for Guangdong Introducing Innovative and Enterpreneurial Teams","award":["2023ZT10X044"],"award-info":[{"award-number":["2023ZT10X044"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/jstsp.2025.3558654","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:49:40Z","timestamp":1744062580000},"page":"623-634","source":"Crossref","is-referenced-by-count":3,"title":["SAV-SE: Scene-Aware Audio-Visual Speech Enhancement With Selective State Space Model"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9511-6713","authenticated-orcid":false,"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"given":"Jiaran","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"given":"Yaodan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5089-6317","authenticated-orcid":false,"given":"Qiquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Telecommunications, The University of New South Wales, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3998-9229","authenticated-orcid":false,"given":"Hexin","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7449-5726","authenticated-orcid":false,"given":"Leibny Paola Garcia","family":"Perera","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong (Shenzhen), Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2048605"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3045846"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3507575"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2923372"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899233"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2019.01.019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3181782"},{"issue":"17","key":"ref16","first-page":"1","article-title":"A survey on techniques for enhancing speech","volume":"179","author":"Taha","year":"2018","journal-title":"Int. J. Comput. Appl."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref18","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16302"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1955"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602549"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-655"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3225649"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876171"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446337"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref39","first-page":"739","article-title":"Dynamic noise embedding: Noise aware training and adaptation for speech enhancement","volume-title":"Proc. 2020 Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Lee","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038111"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3321975"},{"key":"ref42","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832332"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888514"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3180592"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987209"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-701"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.30420\/456164054"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096390"},{"key":"ref52","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu","year":"2024"},{"key":"ref53","article-title":"VMamba: Visual state space model","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref55","article-title":"Contrastive audio-visual masked autoencoder","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393732"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-780"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-839"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446780"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11054330\/10955264.pdf?arnumber=10955264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:38:26Z","timestamp":1751305106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":67,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3558654","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}