{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:25:05Z","timestamp":1769718305314,"version":"3.49.0"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior (CAPES), Brazil","doi-asserted-by":"publisher","award":["001 for Postgraduate Programs in Associative Form"],"award-info":[{"award-number":["001 for Postgraduate Programs in Associative Form"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3654434","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:50:59Z","timestamp":1768510259000},"page":"10033-10052","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Analysis for Depression Recognition Using Stacked Multilevel Deep Neural Networks"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1567-247X","authenticated-orcid":false,"given":"Filipe Fontinele","family":"De Almeida","sequence":"first","affiliation":[{"name":"Department of Computing, Federal University of Maranhão (UFMA), São Luís, Maranhão, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3938-5089","authenticated-orcid":false,"given":"Kelson","family":"R\u00f4mulo Teixeira Aires","sequence":"additional","affiliation":[{"name":"Department of Computing, Federal University of Piauí (UFPI), Teresina, Piauí, Brazil"}]},{"given":"Andr\u00e9","family":"Castelo Branco Soares","sequence":"additional","affiliation":[{"name":"Department of Computing, Federal University of Piauí (UFPI), Teresina, Piauí, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1484-4111","authenticated-orcid":false,"given":"Laurindo De Sousa","family":"Britto Neto","sequence":"additional","affiliation":[{"name":"Department of Computing, Federal University of Piauí (UFPI), Teresina, Piauí, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8180-4032","authenticated-orcid":false,"given":"Rodrigo De Melo","family":"Souza Veras","sequence":"additional","affiliation":[{"name":"Department of Computing, Federal University of Piauí (UFPI), Teresina, Piauí, Brazil"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Depressive Disorder (depression)","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2020.11.073"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0022022119901297"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28296-6_60"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12113"},{"key":"ref9","article-title":"Multimodal depression detection: An investigation of features and fusion techniques for automated systems","author":"Morales","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2022.905917"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2018.00105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2024.1355734"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ComPE49325.2020.9200001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124852"},{"key":"ref15","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","volume-title":"Proc. LREC","author":"Gratch"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21483"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01211-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988263"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133945"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2870398"},{"key":"ref23","article-title":"Measuring depression symptom severity from spoken language and 3D facial expressions","author":"Haque","year":"2018","journal-title":"arXiv:1811.08592"},{"key":"ref24","article-title":"Multimodal fusion with deep neural networks for audio-video emotion recognition","author":"Ortega","year":"2019","journal-title":"arXiv:1907.03196"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683027"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2522"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2019.2925204"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2283"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102872"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413486"},{"key":"ref31","article-title":"A topic-attentive transformer-based model for multimodal depression detection","author":"Guo","year":"2022","journal-title":"arXiv:2206.13256"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/su14063569"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25075-0_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-021-01020-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3154332"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3224135"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104561"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14351-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.103986"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282704"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3362233"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56027-9_12"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2023.03.007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3350071"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-024-00311-9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446491"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13224544"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/computation13010009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3529348"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102861"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889975"},{"key":"ref52","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2025.3550419"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/coin.70019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108561"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3567028"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2008.06.026"},{"key":"ref58","volume-title":"Diagnostic and Statistical Manual of Mental Disorders: Text Revision (DSM-5-TR)","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1046\/j.1525-1497.2001.016009606.x"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383491"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-024-02611-7"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119293"},{"issue":"1","key":"ref64","first-page":"19","article-title":"MFCC and its applications in speaker recognition","volume":"1","author":"Tiwari","year":"2010","journal-title":"Int. J. Emerg. Technol."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3045025"},{"key":"ref69","first-page":"45","article-title":"Software framework for topic modelling with large corpora","volume-title":"Proc. Workshop New Challenges NLP Frameworks","author":"\u0158eh\u016f\u0159ek"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"issue":"60","key":"ref71","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s44184-023-00040-z"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref74","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012","journal-title":"arXiv:1207.0580"},{"key":"ref75","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref76","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Li"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3390\/su142113998"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref79","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref86","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Prokhorenkova"},{"key":"ref87","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3390\/app10072322"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.36871\/ek.up.p.r.2024.12.08.009"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01362"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13140"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21686-2_43"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.07.042"},{"key":"ref96","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lundberg"},{"issue":"1","key":"ref97","first-page":"21","article-title":"Power comparisons of shapiro-wilk, Kolmogorov\u2013Smirnov, Lilliefors and anderson-darling tests","volume":"2","author":"Razali","year":"2011","journal-title":"J. Stat. Model. Anal."},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491.MR0022058.Zbl0041.26103"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.20982\/tqmp.04.1.p013"},{"key":"ref100","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103632"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661807"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11355436.pdf?arnumber=11355436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T09:43:07Z","timestamp":1769679787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11355436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3654434","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}