{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:45:55Z","timestamp":1775871955855,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Korea Government [Ministry of Science and ICT (MSIT)]","doi-asserted-by":"publisher","award":["RS-2023-00219107"],"award-info":[{"award-number":["RS-2023-00219107"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Artificial Intelligence Convergence Innovation Human Resources Development"},{"DOI":"10.13039\/501100003621","name":"Korea Government","doi-asserted-by":"publisher","award":["IITP-2023-RS-2023-00256629"],"award-info":[{"award-number":["IITP-2023-RS-2023-00256629"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019780","name":"Chonnam National University Hwasun Hospital, Institute for Biomedical Science","doi-asserted-by":"publisher","award":["HCRI 23026"],"award-info":[{"award-number":["HCRI 23026"]}],"id":[{"id":"10.13039\/501100019780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3362233","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:42:13Z","timestamp":1707158533000},"page":"20479-20489","source":"Crossref","is-referenced-by-count":44,"title":["Additive Cross-Modal Attention Network (ACMA) for Depression Detection Based on Audio and Textual Features"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9704-8056","authenticated-orcid":false,"given":"Ngumimi Karen","family":"Iyortsuun","sequence":"first","affiliation":[{"name":"Department of AI Convergence, Chonnam National University, Gwangju, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3575-5035","authenticated-orcid":false,"given":"Soo-Hyung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of AI Convergence, Chonnam National University, Gwangju, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-5060","authenticated-orcid":false,"given":"Hyung-Jeong","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of AI Convergence, Chonnam National University, Gwangju, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4221-3058","authenticated-orcid":false,"given":"Seung-Won","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of AI Convergence, Chonnam National University, Gwangju, Republic of Korea"}]},{"given":"Min","family":"Jhon","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Chonnam National University Hospital, Hwasun, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0030442"},{"key":"ref2","volume-title":"Clinical Depression: What Does that Mean?","author":"Daniel","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11030285"},{"key":"ref4","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","volume-title":"Proc. Lang. Resour. Eval. Conf. (LREC)","author":"Gratch"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0224365"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-021-01001-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988269"},{"issue":"3","key":"ref9","first-page":"143","article-title":"Comparison of environmental sound classification performance of convolutional neural networks according to audio preprocessing methods","volume":"39","author":"Oh","year":"2020","journal-title":"J. Acoust. Soc. Korea"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"},{"key":"ref12","first-page":"310","article-title":"A comparative study of filter bank spacing for speech recognition","volume-title":"Proc. Microelectronic Eng. Res. Conf.","author":"Shannon"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116076"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3248654"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104499"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TENSYMP50017.2020.9231008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133950"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52586\/5066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(02)00491-1"},{"issue":"2","key":"ref22","first-page":"117","article-title":"Selective tuning visual attention model","volume":"2","author":"Amudha","year":"2009","journal-title":"Int. J. Recent Trends Eng."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2008.06.026"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app10238701"},{"key":"ref28","article-title":"Universal sentence encoder","author":"Cer","year":"2018","journal-title":"arXiv:1803.11175"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref30","article-title":"Multi-modal depression estimation based on sub-attentional fusion","author":"Wei","year":"2022","journal-title":"arXiv:2207.06180"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1117\/12.2662620"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683027"},{"key":"ref33","article-title":"Measuring depression symptom severity from spoken language and 3D facial expressions","author":"Haque","year":"2018","journal-title":"arXiv:1811.08592"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx761"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746569"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10419326.pdf?arnumber=10419326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T10:10:16Z","timestamp":1709460616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10419326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3362233","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}