{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:07:52Z","timestamp":1767262072299,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["340125"],"award-info":[{"award-number":["340125"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023345","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"1136-1143","source":"Crossref","is-referenced-by-count":2,"title":["Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations"],"prefix":"10.1109","author":[{"given":"Themos","family":"Stafylakis","sequence":"first","affiliation":[{"name":"Omilia - Conversational Intelligence,Athens,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ladislav","family":"Mosner","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sofoklis","family":"Kakouros","sequence":"additional","affiliation":[{"name":"University of Helsinki,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oldrich","family":"Plchot","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Burget","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Cernocky","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TASLP.2021.3122291"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.21437\/interspeech.2021-1280"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/jstsp.2022.3188113"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/interspeech.2021-1775"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2018.8461375"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ISCSLP49672.2021.9362097"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/interspeech.2021-1442"},{"key":"ref8","first-page":"2414","article-title":"Image style transfer using convolutional neural net-works","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Leon"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2018.8461282"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref12","article-title":"Ro-bust Speaker Recognition with Transformers Using wav2vec 2.0","author":"Novoselov","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref15","article-title":"NIST SRE CTS Superset: A large-scale dataset for telephony speaker recognition","author":"Sadjadi","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/j.csl.2019.101032"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Odyssey.2022-49"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICASSP43922.2022.9746952"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.21437\/Interspeech.2018-1929"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref21","article-title":"Emotion recognition from speech","author":"Venkataramanan","year":"2019","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Interspeech.2021-703"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/s10579-008-9076-6"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1016\/j.neunet.2017.02.013"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1007\/978-3-030-80209-7_11"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023345.pdf?arnumber=10023345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:38:18Z","timestamp":1707813498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023345","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}