{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:14:24Z","timestamp":1735103664765,"version":"3.32.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,24]]},"DOI":"10.1109\/biocas61083.2024.10798276","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:10:53Z","timestamp":1734981053000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Two-Stage Cross-Modal Speech Separation Based on Speech Embeddings"],"prefix":"10.1109","author":[{"given":"Yuanjie","family":"Deng","sequence":"first","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinggang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University,School of Control Science and Engineering,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wei","sequence":"additional","affiliation":[{"name":"Shandong University Industrial Technology Research Institute of Shandong Province,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054528"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1117\/12.2641355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"issue":"6","key":"ref15","first-page":"1601","article-title":"Survey of multimodal deep learning","volume":"37","author":"Liu","year":"2020","journal-title":"Appl Res Comput"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413491"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1065"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054180"},{"article-title":"Audiovisual speech separation based on joint feature representation with cross-modal attention","year":"2022","author":"Xiong","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICICSP48821.2019.8958547"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053697"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414133"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987209"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1617"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1955"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"article-title":"BSS_EVAL toolbox user guide-Revision 2.0","year":"2005","author":"F\u00e9votte","key":"ref32"}],"event":{"name":"2024 IEEE Biomedical Circuits and Systems Conference (BioCAS)","start":{"date-parts":[[2024,10,24]]},"location":"Xi'an, China","end":{"date-parts":[[2024,10,26]]}},"container-title":["2024 IEEE Biomedical Circuits and Systems Conference (BioCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10798096\/10798098\/10798276.pdf?arnumber=10798276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:40:19Z","timestamp":1735022419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10798276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,24]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/biocas61083.2024.10798276","relation":{},"subject":[],"published":{"date-parts":[[2024,10,24]]}}}