{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:06Z","timestamp":1784041086754,"version":"3.55.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650095","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy"],"prefix":"10.1109","author":[{"given":"Wenxuan","family":"Wu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096923"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096814"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.216"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.5035693"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2545"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097232"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747315"},{"key":"ref19","first-page":"7193","article-title":"Unsupervised multi-scale expressive speaking style modeling with hierarchical context information for audiobook speech synthesis","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446352"},{"key":"ref21","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096876"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445949"},{"key":"ref27","article-title":"Learning audiovisual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096311"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095295"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1065"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.07.001"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000201"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref40","first-page":"arXiv:1212.6350","author":"Basterrech","year":"2012","journal-title":"Single-sided Real-time PESQ Score Estimation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650095.pdf?arnumber=10650095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:50:02Z","timestamp":1725943802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650095","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}