{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:24:05Z","timestamp":1780392245191,"version":"3.54.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097110","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Multilevel Transformer for Multimodal Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Junyi","family":"He","sequence":"first","affiliation":[{"name":"360 DigiTech,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meimei","family":"Wu","sequence":"additional","affiliation":[{"name":"360 DigiTech,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"360 DigiTech,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Zhu","sequence":"additional","affiliation":[{"name":"360 DigiTech,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Ye","sequence":"additional","affiliation":[{"name":"360 DigiTech,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"835","article-title":"Emotion recognition using mel-frequency cepstral coefficients","volume":"2","author":"Sato","year":"2007","journal-title":"IMT"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10230"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-158"},{"key":"ref4","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT","author":"Devlin"},{"key":"ref5","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"ICLR","author":"Lan"},{"key":"ref6","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","author":"Baevski"},{"key":"ref9","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"ICLR","author":"Baevski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09958-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2007.367230"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953131"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-200"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref23","article-title":"Highway networks","volume-title":"CoRR","author":"Srivastava"},{"key":"ref24","article-title":"Bidirectional attention flow for machine comprehension","volume-title":"ICLR","author":"Seo"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref27","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume":"15","author":"Glorot","year":"2011","journal-title":"AISTATS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1852"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.417"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1353"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097110.pdf?arnumber=10097110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:14:03Z","timestamp":1710368043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097110","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}