{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:44:42Z","timestamp":1778694282292,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446253","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6790-6794","source":"Crossref","is-referenced-by-count":12,"title":["Fusing Multi-Level Features from Audio and Contextual Sentence Embedding from Text for Interview-Based Depression Detection"],"prefix":"10.1109","author":[{"given":"Junqi","family":"Xue","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihan","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinxu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation Harbin Institute of Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Depression and other common mental disorders: global health estimates","volume-title":"Tech. Rep","author":"Health Organization","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.713823"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandc.2004.05.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9924(84)90013-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846256"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747462"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-2522"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746569"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3224135"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.031"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.202"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00611"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref23","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","author":"Gratch","year":"2014","journal-title":"LREC"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446253.pdf?arnumber=10446253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:07:23Z","timestamp":1722575243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446253","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}