{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:25Z","timestamp":1774419625320,"version":"3.50.1"},"reference-count":23,"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\/icassp49660.2025.10889582","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":0,"title":["ITMO language diarization and identification systems for the DISPLACE 2024 challenge"],"prefix":"10.1109","author":[{"given":"Egor","family":"Ausev","sequence":"first","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":"Sergey","family":"Novoselov","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":"Ekaterina","family":"Shangina","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Logunov","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Baevski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1790"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-971X.1989.tb00678.x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref12","article-title":"MUSAN: a music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref13","article-title":"Room impulse response and noise database","author":"Povey","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-53"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"issue":"97","key":"ref19","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004031"},{"key":"ref22","article-title":"Silero VAD: pre-trained enterprise-grade voice activity detector (VAD), number detector and language classifier","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1833"}],"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\/10889582.pdf?arnumber=10889582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:49Z","timestamp":1774416229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889582","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}