{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:01:01Z","timestamp":1776888061072,"version":"3.51.2"},"reference-count":28,"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\/icassp49660.2025.10889156","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":7,"title":["Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment"],"prefix":"10.1109","author":[{"given":"Xuechen","family":"Wang","sequence":"first","affiliation":[{"name":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"}]},{"given":"Shiwan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"}]},{"given":"Haoqin","family":"Sun","sequence":"additional","affiliation":[{"name":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"}]},{"given":"Jiaming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai Unversity,TMCC, College of Computer Science,Tianjin,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP51612.2020.9317379"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-842"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11480"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173989"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-158"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447667"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICUS52573.2021.9641435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145287"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3304"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2067"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095855"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49660.2025.10888086","article-title":"M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper","volume-title":"Proc. arXiv","author":"Zhou"},{"key":"ref19","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":"ref20","first-page":"4171","article-title":"BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095798"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096709"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-523"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-413"},{"issue":"2605","key":"ref28","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"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\/10889156.pdf?arnumber=10889156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:26Z","timestamp":1774416386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889156","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}