{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T00:21:23Z","timestamp":1723854083630},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10627296","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"595-599","source":"Crossref","is-referenced-by-count":0,"title":["Training Strategies for Modality Dropout Resilient Multi-Modal Target Speaker Extraction"],"prefix":"10.1109","author":[{"given":"Srikanth","family":"Korse","sequence":"first","affiliation":[{"name":"International Audio Laboratories Erlangen,Erlangen,Germany,91058"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elminshawi","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen,Erlangen,Germany,91058"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanu\u00ebl A. P.","family":"Habets","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen,Erlangen,Germany,91058"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srikanth Raj","family":"Chetupalli","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen,Erlangen,Germany,91058"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-0882-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1513"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418840"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01957"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11140"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref23"},{"article-title":"New insights on target speaker extraction","year":"2022","author":"Elminshawi","key":"ref24"},{"key":"ref25","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Intl. Conf. on Learn. Repr. (ICLR)","author":"Kingma"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref28"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10627296.pdf?arnumber=10627296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:51:47Z","timestamp":1723787507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10627296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10627296","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}