{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T23:01:30Z","timestamp":1762642890422},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096732","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Dual-Path Cross-Modal Attention for Better Audio-Visual Speech Extraction"],"prefix":"10.1109","author":[{"given":"Zhongweiyang","family":"Xu","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]},{"given":"Xulin","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3024218"},{"key":"ref12","first-page":"111","article-title":"Attention-based audiovisual fusion for robust automatic speech recognition","author":"sterpu","year":"2018","journal-title":"Proceedings of the 20th ACM International Conference on Multi-modal Interaction"},{"article-title":"Multi-talker speech separation with utterance-level permutation invariant training of deep recurrent neural networks","year":"2017","author":"kolb\u00e6k","key":"ref34"},{"key":"ref15","article-title":"Lip2audspec: Speech reconstruction from silent lip movements video","author":"akbari","year":"2017","journal-title":"CoRR"},{"article-title":"Attention bottlenecks for multimodal fusion","year":"2022","author":"nagrani","key":"ref14"},{"article-title":"Librimix: An open-source dataset for generalizable speech separation","year":"2020","author":"cosentino","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref11","article-title":"Recurrent neural network transducer for audio-visual speech recognition","author":"garcia","year":"0","journal-title":"Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop"},{"article-title":"Adam: A method for stochastic opti-mization","year":"2017","author":"kingma","key":"ref33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383539"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref27","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"afouras","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","year":"0","author":"shi","key":"ref9"},{"article-title":"Voice separation with an unknown number of multiple speakers","year":"2020","author":"nachmani","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096732.pdf?arnumber=10096732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:42Z","timestamp":1700506902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096732","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}