{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T02:28:52Z","timestamp":1782268132304,"version":"3.54.5"},"reference-count":27,"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\/icassp49660.2025.10889058","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":6,"title":["CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification"],"prefix":"10.1109","author":[{"given":"Junyi","family":"Peng","sequence":"first","affiliation":[{"name":"Brno University of Technology,Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ladislav","family":"Mo\u0161ner","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Old\u0159ich","family":"Plchot","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Themos","family":"Stafylakis","sequence":"additional","affiliation":[{"name":"Athens University of Economics and Business,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luk\u00e1\u0161","family":"Burget","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"\u010cernock\u00fd","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Speech@FIT,Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389795"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-14"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094795"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-453"},{"key":"ref11","article-title":"Low-resource self-supervised learning with ssl-enhanced tts","author":"Hsu","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022775"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1212"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419426"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref27","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"}],"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\/10889058.pdf?arnumber=10889058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:54Z","timestamp":1774416414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889058","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}