{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:52:42Z","timestamp":1776444762352,"version":"3.51.2"},"reference-count":42,"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\/icassp49660.2025.10889905","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":1,"title":["In Search of Optimal Pretraining Strategy for Robust Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Nikita","family":"Khmelev","sequence":"first","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stepan","family":"Malykh","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandr","family":"Anikin","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasia","family":"Korenevskaya","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Novoselov","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Volokhov","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zorkina","family":"Anastasia","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislav","family":"Marchevskiy","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Galina","family":"Lavrentyeva","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447037"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref5","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","article-title":"UniSpeech-SAT: Universal speech representation learning with speaker aware pre-training","volume-title":"CoRR","volume":"abs\/2110.05752","author":"Chen","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-881"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-49"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1212"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"CoRR","volume":"abs\/1810.04805","author":"Devlin","year":"2018"},{"key":"ref22","article-title":"SpeechBrain: A generalpurpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414704"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-26"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref30","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref35","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1837"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-38"},{"key":"ref40","article-title":"The NIST 2021 speaker recognition evaluation plan","author":"Sadjadi","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1515"},{"key":"ref42","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"}],"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\/10889905.pdf?arnumber=10889905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:42Z","timestamp":1774416162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889905","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}