{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:20Z","timestamp":1777889660309,"version":"3.51.4"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01988","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21408-21418","source":"Crossref","is-referenced-by-count":0,"title":["CogCM: Cognition-Inspired Contextual Modeling for Audio-Visual Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Feixiang","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Lab of AI Safety"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Lab of AI Safety"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Lab of AI Safety"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Lab of AI Safety"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-860"},{"key":"ref2","author":"Afouras","year":"2018","journal-title":"LRS3-TED: a large-scale dataset for visual speech recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109524"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.10.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-517"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832332"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3293758"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref19","article-title":"Learning joint statistical models for audio-visual fusion and segregation","volume":"13","author":"Fisher","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"2031","article-title":"Metricgan: Generative adversarial networks based blackbox metric scores optimization for speech enhancement","volume-title":"ICML","author":"Fu","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-43"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/AVSEC.2024-5"},{"key":"ref28","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2021.07.019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041110"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054528"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888514"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref40","article-title":"Spmamba: State-space model is all you need in speech separation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3384034"},{"key":"ref42","article-title":"Iianet: An intra- and inter-modality attention network for audiovisual speech separation","author":"Li","year":"2024","journal-title":"ICML. OpenReview.net"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125432"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163086"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref46","article-title":"Separate and diffuse: Using a pretrained diffusion model for improving source separation","author":"Lutati","year":"2023","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1482"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.006"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7951787"},{"key":"ref55","article-title":"Rtfs-net: Recurrent time-frequency modelling for efficient audio-visual speech separation","author":"Pegg","year":"2024","journal-title":"ICLR. OpenReview.net"},{"key":"ref56","article-title":"Gan-based speech enhancement for low SNR using latent feature conditioning","author":"Shetu","year":"2024","journal-title":"CoRR"},{"key":"ref57","article-title":"Learning audio-visual speech representation by masked multi-modal cluster prediction","author":"Shi","year":"2022","journal-title":"ICLR. OpenReview.net"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainres.2006.08.123"},{"key":"ref60","first-page":"709","article-title":"Audio\/visual independent components","volume-title":"Proc. ICA","author":"Smaragdis","year":"2003"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054230"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainres.2013.09.010"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10962"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10962"},{"key":"ref65","author":"Thiemann","journal-title":"DEMAND: a collection of multi-channel recordings of acoustic noise in diverse environments"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/AVSEC.2024-9"},{"key":"ref67","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref69","article-title":"Dual attention for audio-visual speech enhancement with facial cues","volume-title":"34th British Machine Vision Conference 2023, BMVC 2023, Aberdeen, UK, November 20\u201324, 2023","author":"Wang","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref72","first-page":"4835","article-title":"Deep multi-modal fusion by channel exchanging","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref75","first-page":"1","article-title":"Target speech extraction with pre-trained avhubert and mask-and-recover strategy","volume-title":"IJCNN","author":"Wu","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275873"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107152"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446058.pdf?arnumber=11446058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:10Z","timestamp":1777612510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01988","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}