{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T03:43:59Z","timestamp":1792813439927,"version":"4.5.0"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["N25BJD005"],"award-info":[{"award-number":["N25BJD005"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20701"],"award-info":[{"award-number":["U24A20701"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2022"],"award-info":[{"award-number":["U22A2022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076059"],"award-info":[{"award-number":["62076059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3300203"],"award-info":[{"award-number":["2024YFC3300203"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Liaoning Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2025-BS-0406"],"award-info":[{"award-number":["2025-BS-0406"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001839","name":"University Grants Committee","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001839","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"publisher","award":["BK20240272"],"award-info":[{"award-number":["BK20240272"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018562","name":"Social Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018562","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108820","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T16:47:42Z","timestamp":1773074862000},"page":"108820","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["DisNet : Learning interpretable depression representations in speech"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3783-4605","authenticated-orcid":false,"given":"Wenju","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7859-2769","authenticated-orcid":false,"given":"Peng","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8729-1133","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5982-2303","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108820_bib0001","series-title":"Interspeech","first-page":"1716","article-title":"Detecting depression with audio\/text sequence modeling of interviews","author":"Al Hanai","year":"2018"},{"issue":"7981","key":"10.1016\/j.neunet.2026.108820_bib0002","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1038\/s41586-023-06541-3","article-title":"Cingulate dynamics track depression recovery with deep brain stimulation","volume":"622","author":"Alagapan","year":"2023","journal-title":"Nature"},{"issue":"3","key":"10.1016\/j.neunet.2026.108820_bib0003","article-title":"Lifetime prevalence and age-of-onset distributions of mental disorders in the Saudi national mental health survey","volume":"29","author":"Altwaijri","year":"2020","journal-title":"International Journal of Methods in Psychiatric Research"},{"key":"10.1016\/j.neunet.2026.108820_bib0004","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"},{"issue":"1","key":"10.1016\/j.neunet.2026.108820_bib0005","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM Journal on Imaging Sciences"},{"issue":"1","key":"10.1016\/j.neunet.2026.108820_bib0006","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1038\/s41398-023-02594-0","article-title":"Relative importance of speech and voice features in the classification of schizophrenia and depression","volume":"13","author":"Berardi","year":"2023","journal-title":"Translational Psychiatry"},{"issue":"1","key":"10.1016\/j.neunet.2026.108820_bib0007","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1038\/s41597-022-01211-x","article-title":"A multi-modal open dataset for mental-disorder analysis","volume":"9","author":"Cai","year":"2022","journal-title":"Scientific Data"},{"key":"10.1016\/j.neunet.2026.108820_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102017","article-title":"IIFDD: Intra and inter-modal fusion for depression detection with multi-modal information from internet of medical things","volume":"102","author":"Chen","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108820_bib0009","series-title":"Icassp 2023-2023 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"Exploring wav2vec 2.0 fine tuning for improved speech emotion recognition","author":"Chen","year":"2023"},{"issue":"6","key":"10.1016\/j.neunet.2026.108820_bib0010","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10.1016\/j.neunet.2026.108820_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15750","article-title":"Exploring simple siamese representation learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2026.108820_bib0012","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.specom.2015.03.004","article-title":"A review of depression and suicide risk assessment using speech analysis","volume":"71","author":"Cummins","year":"2015","journal-title":"Speech Communication"},{"key":"10.1016\/j.neunet.2026.108820_bib0013","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., & Schuller, B. (2010). Opensmile: The munich versatile and fast open-source audio feature extractor (pp. 1459\u20131462). 10.1145\/1873951.1874246.","DOI":"10.1145\/1873951.1874246"},{"key":"10.1016\/j.neunet.2026.108820_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2022.104561","article-title":"A multimodal fusion model with multi-level attention mechanism for depression detection","volume":"82","author":"Fang","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.neunet.2026.108820_bib0015","series-title":"Icassp 2023-2023 ieee international conference on acoustics, speech and signal processing (icassp)","first-page":"1","article-title":"A knowledge-driven vowel-based approach of depression classification from speech using data augmentation","author":"Feng","year":"2023"},{"key":"10.1016\/j.neunet.2026.108820_bib0016","series-title":"Lrec","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","author":"Gratch","year":"2014"},{"key":"10.1016\/j.neunet.2026.108820_bib0017","series-title":"Assessment of depression","first-page":"143","article-title":"The hamilton rating scale for depression","author":"Hamilton","year":"1986"},{"issue":"1","key":"10.1016\/j.neunet.2026.108820_bib0018","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1109\/TCDS.2023.3273614","article-title":"Spatial\u2013temporal feature network for speech-based depression recognition","volume":"16","author":"Han","year":"2023","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"10.1016\/j.neunet.2026.108820_bib0019","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.jbi.2018.05.007","article-title":"Automated depression analysis using convolutional neural networks from speech","volume":"83","author":"He","year":"2018","journal-title":"Journal of Biomedical Informatics"},{"key":"10.1016\/j.neunet.2026.108820_bib0020","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.inffus.2021.10.012","article-title":"Deep learning for depression recognition with audiovisual cues: A review","volume":"80","author":"He","year":"2022","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108820_bib0021","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"5","key":"10.1016\/j.neunet.2026.108820_bib0022","doi-asserted-by":"crossref","first-page":"6830","DOI":"10.1109\/TCSS.2024.3416029","article-title":"Parallel multiscale bridge fusion network for audio\u2013visual automatic depression assessment","volume":"11","author":"Hu","year":"2024","journal-title":"IEEE Transactions on Computational Social Systems"},{"issue":"12","key":"10.1016\/j.neunet.2026.108820_bib0023","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1016\/S0006-3223(01)01129-5","article-title":"Mood disorders in children and adolescents: An epidemiologic perspective","volume":"49","author":"Kessler","year":"2001","journal-title":"Biological Psychiatry"},{"issue":"9","key":"10.1016\/j.neunet.2026.108820_bib0024","doi-asserted-by":"crossref","first-page":"509","DOI":"10.3928\/0048-5713-20020901-06","article-title":"The PHQ-9: A new depression diagnostic and severity measure","volume":"32","author":"Kroenke","year":"2002","journal-title":"Psychiatric Annals"},{"issue":"3","key":"10.1016\/j.neunet.2026.108820_bib0025","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1037\/0021-843X.112.3.353","article-title":"Psychosocial functioning of young adults who have experienced and recovered from major depressive disorder during adolescence","volume":"112","author":"Lewinsohn","year":"2003","journal-title":"Journal of Abnormal Psychology"},{"key":"10.1016\/j.neunet.2026.108820_bib0026","series-title":"Proceedings of the 6th international workshop on audio\/visual emotion challenge","first-page":"35","article-title":"DepAudioNet: An efficient deep model for audio based depression classification","author":"Ma","year":"2016"},{"key":"10.1016\/j.neunet.2026.108820_bib0027","series-title":"Proceedings of 52nd annual meeting of the association for computational linguistics: System demonstrations","first-page":"55","article-title":"The stanford coreNLP natural language processing toolkit","author":"Manning","year":"2014"},{"issue":"12","key":"10.1016\/j.neunet.2026.108820_bib0028","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1002\/jclp.21908","article-title":"The depression anxiety stress scales-21 (DASS-21): Further examination of dimensions, scale reliability, and correlates","volume":"68","author":"Osman","year":"2012","journal-title":"Journal of Clinical Psychology"},{"key":"10.1016\/j.neunet.2026.108820_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2025.110821","article-title":"Sub-band based analysis for speech emotion classification","volume":"239","author":"Pattnaik","year":"2025","journal-title":"Applied Acoustics"},{"key":"10.1016\/j.neunet.2026.108820_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2486","article-title":"A joint cross-attention model for audio-visual fusion in dimensional emotion recognition","author":"Praveen","year":"2022"},{"key":"10.1016\/j.neunet.2026.108820_bib0031","series-title":"2018\u202fIEEE spoken language technology workshop (SLT)","first-page":"1021","article-title":"Speaker recognition from raw waveform with sincnet","author":"Ravanelli","year":"2018"},{"key":"10.1016\/j.neunet.2026.108820_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2021.103107","article-title":"Mfcc-based recurrent neural network for automatic clinical depression recognition and assessment from speech","volume":"71","author":"Rejaibi","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.neunet.2026.108820_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106120","article-title":"A multimodal dynamical variational autoencoder for audiovisual speech representation learning","volume":"172","author":"Sadok","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108820_bib0034","unstructured":"Saire2023 (2023). wav2vec2-base-finetuned-speaker-classification. https:\/\/hf-mirror.com\/Saire2023\/wav2vec2-base-finetuned-Speaker-Classification."},{"issue":"April 2021","key":"10.1016\/j.neunet.2026.108820_bib0035","article-title":"Audio based depression detection using convolutional autoencoder","volume":"189","author":"Sardari","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.108820_bib0036","series-title":"2015\u202fIEEE international conference on acoustics, speech and signal processing (ICASSP)","first-page":"4789","article-title":"Reduced vowel space is a robust indicator of psychological distress: A cross-corpus analysis","author":"Scherer","year":"2015"},{"key":"10.1016\/j.neunet.2026.108820_bib0037","series-title":"Icassp 2022-2022 IEEE international conference on acoustics, speech and signal processing (icassp)","first-page":"6247","article-title":"Automatic depression detection: An emotional audio-textual corpus and a gru\/bilstm-based model","author":"Shen","year":"2022"},{"issue":"6","key":"10.1016\/j.neunet.2026.108820_bib0038","doi-asserted-by":"crossref","first-page":"688","DOI":"10.3390\/e22060688","article-title":"Automatic detection of depression in speech using ensemble convolutional neural networks","volume":"22","author":"V\u00e1zquez-Romero","year":"2020","journal-title":"Entropy"},{"key":"10.1016\/j.neunet.2026.108820_bib0039","doi-asserted-by":"crossref","DOI":"10.2196\/49222","article-title":"Speech features as predictors of momentary depression severity in patients with depressive disorder undergoing sleep deprivation therapy: Ambulatory assessment pilot study","volume":"11","author":"Wadle","year":"2024","journal-title":"JMIR Mental Health"},{"key":"10.1016\/j.neunet.2026.108820_bib0040","series-title":"European conference on computer vision","first-page":"623","article-title":"Multi-modal depression estimation based on sub-attentional fusion","author":"Wei","year":"2022"},{"key":"10.1016\/j.neunet.2026.108820_bib0041","series-title":"Proceedings of the 6th international workshop on audio\/visual emotion challenge","first-page":"11","article-title":"Detecting depression using vocal, facial and semantic communication cues","author":"Williamson","year":"2016"},{"key":"10.1016\/j.neunet.2026.108820_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128209","article-title":"Attention-based acoustic feature fusion network for depression detection","volume":"601","author":"Xu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108820_bib0043","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neunet.2023.05.041","article-title":"Attention guided learnable time-domain filterbanks for speech depression detection","volume":"165","author":"Yang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108820_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106943","article-title":"Bpen: Brain posterior evidential network for trustworthy brain imaging analysis","volume":"183","author":"Ye","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108820_bib0045","doi-asserted-by":"crossref","first-page":"9422","DOI":"10.52202\/075280-0413","article-title":"White-box transformers via sparse rate reduction","volume":"36","author":"Yu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108820_bib0046","unstructured":"Yu, Y., Chu, T., Tong, S., Wu, Z., Pai, D., Buchanan, S., & Ma, Y. (2024). Emergence of segmentation with minimalistic white-box transformers (pp. 72\u201393). https:\/\/openreview.net\/forum?id=kmzH8kT9TE."},{"key":"10.1016\/j.neunet.2026.108820_bib0047","unstructured":"Zeghidour, N., Teboul, O., de Chaumont Quitry, F., & Tagliasacchi, M. (2021). Leaf: A learnable frontend for audio classification. ICLR. https:\/\/openreview.net\/forum?id=jM76BCb6F9m."},{"key":"10.1016\/j.neunet.2026.108820_bib0048","series-title":"Proceedings of the 29th ACM international conference on multimedia","first-page":"135","article-title":"Depa: Self-supervised audio embedding for depression detection","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108820_bib0049","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3510","article-title":"Robust lightweight facial expression recognition network with label distribution training","volume":"vol. 35","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neunet.2026.108820_bib0050","series-title":"2022 44th annual international conference of the IEEE engineering in medicine & biology society (EMBC)","first-page":"3409","article-title":"Unaligned multimodal sequences for depression assessment from speech","author":"Zhao","year":"2022"},{"issue":"4","key":"10.1016\/j.neunet.2026.108820_bib0051","doi-asserted-by":"crossref","first-page":"2823","DOI":"10.1109\/TAFFC.2022.3181210","article-title":"Semi-structural interview-based chinese multimodal depression corpus towards automatic preliminary screening of depressive disorders","volume":"14","author":"Zou","year":"2022","journal-title":"IEEE Transactions on Affective Computing"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002820?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002820?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:21:25Z","timestamp":1786634485000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002820"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":51,"alternative-id":["S0893608026002820"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108820","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DisNet : Learning interpretable depression representations in speech","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108820","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108820"}}