{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:23:49Z","timestamp":1774448629759,"version":"3.50.1"},"reference-count":26,"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\/icasspw59220.2023.10193049","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":11,"title":["Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings"],"prefix":"10.1109","author":[{"given":"I-Chun","family":"Chern","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Kuo-Hsuan","family":"Hung","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Yi-Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}]},{"given":"Tassadaq","family":"Hussain","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,UK"}]},{"given":"Mandar","family":"Gogate","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,UK"}]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,UK"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}]},{"given":"Jen-Cheng","family":"Hou","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3181782"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-763"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref10","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-885"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","author":"hu","year":"0","journal-title":"100 nonspeech environmental sounds"},{"key":"ref18","year":"0","journal-title":"Dlib face detector library"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref20","article-title":"LRS3TED: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv preprint arXiv 1809 00496"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc ICLR"},{"key":"ref8","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"shi","year":"2022","journal-title":"arXiv preprint arXiv 2201 02184"},{"key":"ref7","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746449"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153265"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00139"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193049.pdf?arnumber=10193049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:24Z","timestamp":1692639744000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193049","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}