{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:12:33Z","timestamp":1776881553105,"version":"3.51.2"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889409","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Level Speaker Representation for Target Speaker Extraction"],"prefix":"10.1109","author":[{"given":"Ke","family":"Zhang","sequence":"first","affiliation":[{"name":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China"}]},{"given":"Junjie","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Hong Kong,China"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,SDS, SRIBD,Shenzhen,China"}]},{"given":"Yangjie","family":"Wei","sequence":"additional","affiliation":[{"name":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University,Key Laboratory of Intelligent Computing in Medical Image,China"}]},{"given":"Yannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent,Tencent Ethereal Audio Lab,Shenzhen,China"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,SDS, SRIBD,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095609"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1234"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1130"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1939"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10767"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448398"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2545"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3175130"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-176"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-655"},{"issue":"17","key":"ref18","first-page":"18 815","article-title":"Self-supervised disentangled representation learning for robust target speech extraction","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Mu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096478"},{"key":"ref20","article-title":"Improving target speaker extraction with sparse lda-transformed speaker embeddings","author":"Liu","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3324550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447529"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447832"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448315"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3383794"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","article-title":"Spectral features for automatic text-independent speaker recognition","volume-title":"Licentiate\u2019s thesis","author":"Kinnunen","year":"2003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref31","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Advances in Neural Information Processing Systems","volume":"13","author":"Lee","year":"2000"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876726"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref34","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1840"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747340"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1560"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832217"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889409.pdf?arnumber=10889409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:05Z","timestamp":1774416185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889409\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889409","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}