{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:17:49Z","timestamp":1770830269514,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62272172"],"award-info":[{"award-number":["62272172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Science Foundation","award":["2023A1515012920"],"award-info":[{"award-number":["2023A1515012920"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3324550","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T18:10:57Z","timestamp":1697220657000},"page":"178-188","source":"Crossref","is-referenced-by-count":5,"title":["Contrastive Learning for Target Speaker Extraction With Attention-Based Fusion"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7318-7879","authenticated-orcid":false,"given":"Xiao","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruirui","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Economics and Finance, Brunel University London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huichou","family":"Huang","sequence":"additional","affiliation":[{"name":"Global Research Unit, City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6771-3932","authenticated-orcid":false,"given":"Qingyao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054311"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11183"},{"key":"ref34","first-page":"614","article-title":"A target speaker separation neural network with joint-training","author":"yang","year":"0","journal-title":"Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2260"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1378"},{"key":"ref31","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"henaff","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094306"},{"key":"ref33","article-title":"Semi-supervised time domain target speaker extraction with attention","author":"wang","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3100682"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1606"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/srep34390"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683874"},{"key":"ref38","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2250"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746221"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref23","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref26","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref21","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref28","first-page":"2530","article-title":"CLAR: Contrastive learning of auditory representations","author":"al-tahan","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref29","article-title":"Multi-format contrastive learning of audio representations","author":"wang","year":"2021"},{"key":"ref8","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687903"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1397"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10284995.pdf?arnumber=10284995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:03:46Z","timestamp":1701115426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10284995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3324550","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}