{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:26:08Z","timestamp":1783787168353,"version":"3.55.0"},"reference-count":38,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890812","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":6,"title":["Metadata-Enhanced Speech Emotion Recognition: Augmented Residual Integration and Co-Attention in Two-Stage Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Zixiang","family":"Wan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyue","family":"Qiu","sequence":"additional","affiliation":[{"name":"Arizona State University,Ira A. Fulton Schools of Engineering,Tempe,United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Xingjian College,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"750","article-title":"A multilingual framework based on pre-training model for speech emotion recognition","volume-title":"Proc. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Zhang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-57"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-756"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1434"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1038"},{"key":"ref7","first-page":"5269","article-title":"Cross-lingual\/cross-channel intent detection in contact-center conversations","volume-title":"Proc. Interspeech","author":"Agrawal"},{"key":"ref8","first-page":"684","article-title":"Automated neural nursing assistant (ANNA): An over-the-phone system for cognitive monitoring","volume-title":"Proc. Interspeech","author":"Solinsky"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095522"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2407"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87802-3_55"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-396"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3372806.3372818"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2018.8652301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2271"},{"key":"ref20","first-page":"589","article-title":"A review of speech emotion recognition: Datasets, features, and machine learning algorithms","volume":"11","author":"Schuller","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref21","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462979"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.34"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1683"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","author":"Busso","year":"2008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095193"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096966"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094651"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095777"},{"key":"ref35","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":"ref36","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3184480"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"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\/10890812.pdf?arnumber=10890812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:58Z","timestamp":1774416118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890812","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}