{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:14:42Z","timestamp":1774419282549,"version":"3.50.1"},"reference-count":34,"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\/icassp49660.2025.10888883","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":["SSE: A Speaking Style Extractor Based on Fine-Grained Contrastive Learning between Speech and Descriptive Text"],"prefix":"10.1109","author":[{"given":"Zixing","family":"Zhang","sequence":"first","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yimeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongren","family":"Dong","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wulong","family":"Xiang","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengfan","family":"Shen","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Imperial College London,GLAM,Department of Computing,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.02.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446933"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.358"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447829"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094888"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095997"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11614-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3481003"},{"key":"ref12","article-title":"SEGAA: A unified approach to predicting age, gender, and emotion in speech","author":"Sigicharla","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-023-10241-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref16","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413520"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-129"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref24","volume-title":"English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1163\/9789401206884_014"},{"key":"ref26","first-page":"6532","article-title":"Open-source multi-speaker corpora of the english accents in the british isles","volume-title":"Proc. 12th Language Resources and Evaluation Conference (LREC)","author":"Demirsahin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref28","volume-title":"Surrey audio-visual expressed emotion (SAVEE) database","author":"Jackson","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfludis.2018.03.002"},{"key":"ref30","article-title":"Language models are few-shot learners","author":"Mann","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3297961"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISSC59246.2023.10162075"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-739"}],"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\/10888883.pdf?arnumber=10888883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:03Z","timestamp":1774416123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888883","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}