{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:23:21Z","timestamp":1776889401244,"version":"3.51.2"},"reference-count":37,"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\/icassp49660.2025.10887949","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["A Study of Multi-Scale Feature Learning From Pre-Trained Models on Speaker Verification"],"prefix":"10.1109","author":[{"given":"Shengyu","family":"Peng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuoliang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref3","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"Li","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-405"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3231709"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-402"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3136141"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313431"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8549-4_38"},{"key":"ref13","first-page":"12 449","article-title":"Wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1280"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446612"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022775"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447606"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2024.109929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419426"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-605"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-111"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"key":"ref29","article-title":"Musan: a music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref31","article-title":"The dku-dukeece systems for voxceleb speaker recognition challenge 2020","author":"Wang","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-64"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1558"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-453"}],"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\/10887949.pdf?arnumber=10887949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:52Z","timestamp":1774416232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887949","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}