{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:04Z","timestamp":1784041084977,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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","award":["62401377"],"award-info":[{"award-number":["62401377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091302006"],"award-info":[{"award-number":["ZDSYS20230626091302006"]}]},{"name":"Program for Guangdong Introducing Innovative and Enterpreneurial","award":["2023ZT10X044"],"award-info":[{"award-number":["2023ZT10X044"]}]},{"name":"Shenzhen Science and Technology Research Fund","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/jstsp.2025.3560513","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T13:37:09Z","timestamp":1744724229000},"page":"646-657","source":"Crossref","is-referenced-by-count":3,"title":["$C^{2}$AV-TSE: Context and Confidence-Aware Audio Visual Target Speaker Extraction"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1235-9729","authenticated-orcid":false,"given":"Wenxuan","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiadong","family":"Wang","sequence":"additional","affiliation":[{"name":"Technical University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingwei","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-1572","authenticated-orcid":false,"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-3532","authenticated-orcid":false,"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.5035693"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094306"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650095"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650095"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097232"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/ASRU46091.2019.9003987","article-title":"Improving speech enhancement with phonetic embedding features","volume-title":"Proc. 2019 IEEE Autom. Speech Recognit. Understanding Workshop","author":"Wu","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053845"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2028"},{"key":"ref13","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin","year":"2019"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746765"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-782"},{"key":"ref19","first-page":"1399","article-title":"A $^{3}$ T: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Bai","year":"2022"},{"key":"ref20","first-page":"2223","article-title":"Towards effective and compact contextual representation for conformer transducer speech recognition systems","volume-title":"Proc. Interspeech","author":"Cui","year":"2023"},{"key":"ref21","article-title":"Bigger is not always better: The effect of context size on speech pre-training","author":"Robertson","year":"2023"},{"key":"ref22","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref23","article-title":"MAM: Masked acoustic modeling for end-to-end speech-to-text translation","author":"Chen","year":"2020"},{"key":"ref24","first-page":"12736","article-title":"Fused acoustic and text encoding for multimodal bilingual pretraining and speech translation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng","year":"2021"},{"key":"ref25","first-page":"1","article-title":"Contrastive learning with hard negative samples","volume-title":"Int. Conf. Learn. Representations","author":"Robinson","year":"2021"},{"key":"ref26","first-page":"2999","article-title":"Focal loss for dense object detection","volume-title":"Proc. 2017 IEEE Int. Conf. Comput. Vis.","author":"Lin","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref28","first-page":"7444","article-title":"Mining effective negative training samples for keyword spotting","volume-title":"Proc. 2020 IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Hou","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00547"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref34","first-page":"1","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446625"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref39","first-page":"626","article-title":"SDRhalf-baked or well done?","volume-title":"Proc. 2019 IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Roux","year":"2018"},{"key":"ref40","article-title":"Single-sided real-time PESQ score estimation","author":"Basterrech","year":"2012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11054330\/10964181.pdf?arnumber=10964181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:36Z","timestamp":1770929976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10964181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3560513","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}