{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:56:17Z","timestamp":1772006177943,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFB2808802"],"award-info":[{"award-number":["2024YFB2808802"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/jstsp.2026.3652299","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:02Z","timestamp":1768255262000},"page":"32-46","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Use of Large Language Models and Interpretable Features for Explainable Speech Emotion Recognition"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5016-0094","authenticated-orcid":false,"given":"Qifei","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5881-3723","authenticated-orcid":false,"given":"Yingming","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7059-9196","authenticated-orcid":false,"given":"Yuhua","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingying","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Autonomous Intelligent Unmanned Systems, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1529-1552","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1632-4293","authenticated-orcid":false,"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6284-5039","authenticated-orcid":false,"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.838534"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095193"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094673"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1133"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414540"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108472"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5539-3"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102019","volume":"102","author":"Khare","year":"2024","journal-title":"Inf. Fusion."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3272553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103649"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW59127.2023.10388120"},{"key":"ref14","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Lundberg","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/24751839.2023.2187278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05536-5"},{"key":"ref17","first-page":"6","article-title":"Automated audio captioning with weakly supervised pre-training and word selection methods","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events","author":"Han","year":"2021"},{"key":"ref18","first-page":"40","article-title":"Improving the performance of automated audio captioning via integrating the acoustic and semantic information","volume-title":"Proc. 6th Detection Classification Acoust. Scenes Events","author":"Ye","year":"2021"},{"key":"ref19","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Mach. Learn. Res.","author":"Li","year":"2023"},{"key":"ref20","first-page":"32897","article-title":"VLMO: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"35","author":"Bao","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29902"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448316"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1832"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888198"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888591"},{"key":"ref26","article-title":"InstructERC: Reforming emotion recognition in conversation with a retrieval multi-task LLMs framework","author":"Lei","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref29","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.02.016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-242"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095611"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-756"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref36","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref38","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"32","author":"Ren","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.11.005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128177"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2396"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.056"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2003.1223975"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445977"},{"key":"ref47","first-page":"1","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. SPIE Int. Soc. Opt. Eng.","author":"Tang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref49","article-title":"AffectGPT: Dataset and framework for explainable multimodal emotion recognition","author":"Lian","year":"2024"},{"key":"ref50","article-title":"EMO-LLAMA: Enhancing facial emotion understanding with instruction tuning","author":"Xing","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-962"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446186"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446974"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3221749"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102382"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448213"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095588"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.01.008"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.109178"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235194"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1170"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-80"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448130"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1591"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447829"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653457\/mm1"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11409413\/11345123.pdf?arnumber=11345123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T06:57:53Z","timestamp":1772002673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":76,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2026.3652299","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}