{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:51Z","timestamp":1775230131949,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832179","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"349-356","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Speaker Extraction Through Rectifying Target Confusion"],"prefix":"10.1109","author":[{"given":"Jiahe","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen"}]},{"given":"Junjie","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907373"},{"issue":"1","key":"ref2","first-page":"117","article-title":"The cocktail party phenomenon: A review of research on speech intelligibility in multiple-talker conditions","volume":"86","author":"Bronkhorst","year":"2000","journal-title":"Acta acustica united with acustica"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1073858413514136"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1840"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2545"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1397"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2266"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref10","article-title":"New insights on target speaker extraction","author":"Elminshawi","year":"2022","journal-title":"arXiv preprint arXiv:2202.00733"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095609"},{"key":"ref15","article-title":"Probing deep speaker embeddings for speaker-related tasks","author":"Zhao","year":"2022","journal-title":"arXiv preprint arXiv:2212.07068"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447529"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096664"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746314"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17710"},{"key":"ref25","article-title":"Audio-visual target speaker extraction with reverse selective auditory attention","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv:2404.18501"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11252"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref28","article-title":"But system description to voxceleb speaker recognition challenge 2019","author":"Zeinali","year":"2019","journal-title":"arXiv preprint arXiv:1910.12592"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097210"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447832"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1433"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref34","article-title":"Librimix: An opensource dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint arXiv:2005.11262"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1749"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447529"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448315"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096648"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-655"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832179.pdf?arnumber=10832179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:08:50Z","timestamp":1737101330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832179","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}