{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:41Z","timestamp":1774419941582,"version":"3.50.1"},"reference-count":31,"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\/icassp49660.2025.10888890","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["SoCov: Semi-Orthogonal Parametric Pooling of Covariance Matrix for Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Rongjin","family":"Li","sequence":"first","affiliation":[{"name":"VoiceAI Technologies, Co. Ltd,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weibin","family":"Zhang","sequence":"additional","affiliation":[{"name":"VoiceAI Technologies, Co. Ltd,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"VoiceAI Technologies, Co. Ltd,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Kang","sequence":"additional","affiliation":[{"name":"Ministry of Public Security,Institute of Forensic Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofen","family":"Xing","sequence":"additional","affiliation":[{"name":"South China University of Technology,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICComm.2018.8484753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747792"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2616"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616048"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_37"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362097"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1442"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-45"},{"key":"ref22","article-title":"NIST SRE CTS Superset: A large-scale dataset for telephony speaker recognition","author":"Sadjadi","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref26","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref28","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"The Kaldi speech recognition toolkit","volume-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding","author":"Povey"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054624"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"}],"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\/10888890.pdf?arnumber=10888890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:33Z","timestamp":1774416333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888890","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}