{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:10:13Z","timestamp":1775200213987,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434758","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Intermediate-Selective Feature Enhancement for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Yangbiao","family":"Li","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Future Technology,China"}]},{"given":"Xiaofen","family":"Xing","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}]},{"given":"Jialong","family":"Mai","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}]},{"given":"Jingyuan","family":"Xing","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Future Technology,China"}]},{"given":"Xiangmin","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Future Technology,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-2850.1995.tb00036.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682154"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1885"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-752"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1889"},{"key":"ref9","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3513835"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023428"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref19","article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","author":"Shah","year":"2021","journal-title":"arXiv preprint arXiv:2101.00387"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-651"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1170"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096966"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094651"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094673"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-469"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890812"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446974"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446812"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890265"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890796"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434758.pdf?arnumber=11434758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:23Z","timestamp":1775192363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434758","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}