{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:41:08Z","timestamp":1765438868945,"version":"3.37.3"},"reference-count":18,"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"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icasspw59220.2023.10192961","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":1,"title":["Towards Pose-Invariant Audio-Visual Speech Enhancement in the Wild for Next-Generation Multi-Modal Hearing Aids"],"prefix":"10.1109","author":[{"given":"Mandar","family":"Gogate","sequence":"first","affiliation":[{"name":"Edinburgh Napier University,School of Computing,Scotland,UK"}]},{"given":"Kia","family":"Dashtipour","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,School of Computing,Scotland,UK"}]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University,School of Computing,Scotland,UK"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref12","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv preprint arXiv 1809 00496"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref14","article-title":"Blaze-face: Sub-millisecond neural face detection on mobile gpus","author":"bazarevsky","year":"2019","journal-title":"arXiv preprint arXiv 1907 05047"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref10","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","author":"jaegle","year":"2022","journal-title":"The Tenth International Conferenceon Learning Representations ICLR 2022 Virtual Event April 25-29 2022"},{"key":"ref2","first-page":"186","article-title":"Acoustical aspects of cocktail parties","volume":"38","author":"plomp","year":"1977","journal-title":"Acta Acustica United with Acustica"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref8","article-title":"Attention mesh: High-fidelity face mesh prediction in real-time","author":"grishchenko","year":"2020","journal-title":"arXiv preprint arXiv 2006 10226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2022-2"},{"key":"ref9","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018","journal-title":"arXiv preprint arXiv 1803 01271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app11020721"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10192961.pdf?arnumber=10192961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:45Z","timestamp":1692639765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10192961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10192961","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}