{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:56Z","timestamp":1774419716649,"version":"3.50.1"},"reference-count":31,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890786","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":3,"title":["Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision"],"prefix":"10.1109","author":[{"given":"Yafeng","family":"Chen","sequence":"first","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luyao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1597","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","volume-title":"Proceedings of ICML 2020","author":"Chen"},{"key":"ref2","article-title":"Representation Learning with Contrastive Predictive Coding","author":"Oord","year":"2018","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref5","article-title":"Disentangling Voice and Content with Self-Supervision for Speaker Recognition","volume-title":"Proceedings of NeurIPS 2023","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746411"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402077"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747526"},{"key":"ref9","article-title":"Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning","volume-title":"Proceedings of NeurIPS 2020","author":"Grill"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1202"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022470"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-360"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-354"},{"key":"ref16","article-title":"Self-Supervised Learning with Cluster-Aware-DINO for High-Performance Robust Speaker Verification","author":"Han","year":"2023","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref21","first-page":"448","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","volume-title":"ICML 2015, Lille, France, 6-11 July 2015","volume":"37","author":"Ioffe","year":"2015"},{"key":"ref22","first-page":"971","article-title":"Self-Normalizing Neural Networks","author":"Klambauer","year":"2017","journal-title":"NIPS 2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","first-page":"2292","article-title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport","author":"Cuturi","year":"2013","journal-title":"NIPS 2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref28","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"issue":"11","key":"ref31","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"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\/10890786.pdf?arnumber=10890786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:16Z","timestamp":1774416256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890786\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890786","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}