{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:26:58Z","timestamp":1761895618025,"version":"build-2065373602"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209516","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["MAMF-Net: Modality-Adaptive Masked Fusion Network for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Hengrui","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Lu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Taiyuan University of Technology,School of Software,Taiyuan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopei","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongbing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaohui","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02716-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-023-10037-w"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3163445"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3141237"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533328"},{"journal-title":"Speechbert: Cross-modal pre-trained language model for endto-end spoken question answering","year":"2019","author":"Chuang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"issue":"8","key":"ref10","volume":"3","author":"Lee","year":"2018","journal-title":"Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"journal-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref12"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"journal-title":"Mosi: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","year":"2016","author":"Zadeh","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref17","first-page":"3501","article-title":"Emovo corpus: an italian emotional speech database","volume-title":"Proceedings of the ninth international conference on language resources and evaluation (LREC\u201914)","author":"Costantini"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"volume-title":"Surrey audio-visual expressed emotion (savee) database","year":"2014","author":"Jackson","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"journal-title":"Teasel: a transformer-based speech-prefixed language model","year":"2021","author":"Arjmand","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.197"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612517"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01925"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209516.pdf?arnumber=11209516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:54:20Z","timestamp":1761890060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209516","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}