{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:45:51Z","timestamp":1775871951247,"version":"3.50.1"},"reference-count":19,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"vor","delay-in-days":263,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1016\/j.procs.2025.09.257","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T22:13:24Z","timestamp":1762467204000},"page":"1361-1371","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Depression Detection via Dual Audio Streams and Transformer Fusion"],"prefix":"10.1016","volume":"270","author":[{"given":"Boutheina","family":"Ben-Ismail","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wyssem","family":"Fathallah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bassem Ben","family":"Salah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Hamroun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hedi","family":"Sakli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2025.09.257_bib1","unstructured":"Global Health Organization. (2024). Depression statistics. Journal of Global Mental Health, 15**(3)**: 123\u2013145."},{"issue":"4","key":"10.1016\/j.procs.2025.09.257_bib2","first-page":"512","article-title":"\"Challenges in Clinical Diagnostics.\"","volume":"78","author":"Smith","year":"2023","journal-title":"Journal of Clinical Psychology"},{"issue":"2","key":"10.1016\/j.procs.2025.09.257_bib3","first-page":"89","article-title":"\"DAIC-WOZ: A Resource for Mental Health Analysis.\"","volume":"5","author":"Miller","year":"2023","journal-title":"Journal of Affective Computing"},{"issue":"3","key":"10.1016\/j.procs.2025.09.257_bib4","first-page":"1","article-title":"\"Real-Time Health Monitoring Using AI.\"","volume":"12","author":"Taylor","year":"2024","journal-title":"ACM Health Informatics"},{"issue":"1","key":"10.1016\/j.procs.2025.09.257_bib5","first-page":"45","article-title":"\"Scalability Challenges in AI Diagnostics.\"","volume":"42","author":"Nguyen","year":"2025","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.procs.2025.09.257_bib6","first-page":"1245","article-title":"\"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.\"","volume":"9","author":"Lan","year":"2020","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"10.1016\/j.procs.2025.09.257_bib7","unstructured":"Jones, T., et al. (2016). \"SVM for Audio-Based Depression Detection.\" IEEE FG 2016, 1-8."},{"key":"10.1016\/j.procs.2025.09.257_bib8","unstructured":"Brown, K., et al. (2017). \"Decision Trees for Speech Emotion Recognition.\" ICASSP 2017, 2227-2231."},{"issue":"3","key":"10.1016\/j.procs.2025.09.257_bib9","first-page":"456","article-title":"\"CNNs for Acoustic Feature Extraction in Depression Detection.\"","volume":"9","author":"Lee","year":"2018","journal-title":"IEEE TAC"},{"key":"10.1016\/j.procs.2025.09.257_bib10","unstructured":"Patel, R., et al. (2019). \"RNNs for Sequential Speech Analysis.\" ICML 2019, 6102-6111."},{"key":"10.1016\/j.procs.2025.09.257_bib11","unstructured":"Kim, H., et al. (2023). \"Vision Transformers for DAIC-WOZ Depression Classification.\" CVPR 2023, 12345-12354."},{"issue":"3","key":"10.1016\/j.procs.2025.09.257_bib12","first-page":"1234","article-title":"\"Transformer-based audio-text fusion for multimodal depression detection.\"","volume":"15","author":"Zhao","year":"2024","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"2","key":"10.1016\/j.procs.2025.09.257_bib13","first-page":"210","article-title":"\"Self-Supervised Learning for Mental Health Assessment.\"","volume":"36","author":"Patel","year":"2025","journal-title":"IEEE TNNLS"},{"key":"10.1016\/j.procs.2025.09.257_bib14","unstructured":"Lin, J., et al. (2024). \"Neural Modeling of Speech Transcripts in Depression Detection.\" NeurIPS 2024, 1-12."},{"key":"10.1016\/j.procs.2025.09.257_bib15","first-page":"1","article-title":"\"ALBERT for Emotion Recognition in Clinical Speech.\"","volume":"31","author":"Huang","year":"2024","journal-title":"IEEE SPL"},{"issue":"1","key":"10.1016\/j.procs.2025.09.257_bib16","first-page":"45","article-title":"\"Computational Empathy in Mental Health Support.\"","volume":"10","author":"Sharma","year":"2023","journal-title":"JMIR Mental Health"},{"issue":"1","key":"10.1016\/j.procs.2025.09.257_bib17","first-page":"34","article-title":"\"Temporal Transformers for Speech-Based Depression Screening.\"","volume":"15","author":"Xu","year":"2023","journal-title":"PMC Journal"},{"issue":"4","key":"10.1016\/j.procs.2025.09.257_bib18","first-page":"78","article-title":"\"Spectral Histograms for Depression Detection in Clinical Speech.\"","volume":"12","author":"Gupta","year":"2024","journal-title":"Journal of Affective Disorders"},{"issue":"2","key":"10.1016\/j.procs.2025.09.257_bib19","first-page":"567","article-title":"\"Transformer-based fusion for multimodal depression detection.\"","volume":"21","author":"Zhou","year":"2024","journal-title":"Journal of Neural Engineering"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925029308?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925029308?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T08:35:32Z","timestamp":1766306132000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050925029308"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":19,"alternative-id":["S1877050925029308"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.257","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Depression Detection via Dual Audio Streams and Transformer Fusion","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.257","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}