{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:12:03Z","timestamp":1784301123567,"version":"3.55.0"},"reference-count":37,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003803","name":"University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003803","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\/icassp49357.2023.10097232","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":11,"title":["ImagineNet: Target Speaker Extraction with Intermittent Visual Cue Through Embedding Inpainting"],"prefix":"10.1109","author":[{"given":"Zexu","family":"Pan","sequence":"first","affiliation":[{"name":"National University of Singapore (NUS),Institute of Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wupeng","family":"Wang","sequence":"additional","affiliation":[{"name":"NUS,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marvin","family":"Borsdorf","sequence":"additional","affiliation":[{"name":"University of Bremen,Machine Listening Lab,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data, School of Data Science,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10163-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref34","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref31","first-page":"626","article-title":"SDR–halfbaked or well done?","author":"le roux","year":"2019","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref30","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/JSTSP.2019.2922820","article-title":"SpeakerBeam: Speaker aware neural network for target speaker extraction in speech mixtures","volume":"13","author":"\u017emol\u00edkov\u00e1","year":"2019","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2947232"},{"key":"ref10","first-page":"2728","article-title":"VoiceFilter: Targeted voice separation by speaker-conditioned spectrogram masking","author":"wang","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413488"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11183"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2028"},{"key":"ref24","first-page":"6663","article-title":"Switching variational auto-encoders for noise-agnostic audiovisual speech enhancement","author":"sadeghi","year":"2021","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref23","first-page":"7534","article-title":"Robust unsupervised audiovisual speech enhancement using a mixture of variational autoencoders","author":"sadeghi","year":"2020","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746866"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-157"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1939"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747073"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3175130"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746757"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3243764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190742"},{"key":"ref3","article-title":"Predict-and-update network: Audiovisual speech recognition inspired by human speech perception","author":"wang","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1653"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10097232.pdf?arnumber=10097232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:00Z","timestamp":1700506620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097232","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}