{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T07:07:50Z","timestamp":1778828870640,"version":"3.51.4"},"reference-count":55,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.bspc.2026.110342","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T18:48:45Z","timestamp":1777315725000},"page":"110342","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A model for speech depression detection based on star operation and relative position encoding"],"prefix":"10.1016","volume":"122","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7083-315X","authenticated-orcid":false,"given":"Yuling","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lasheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3809-3465","authenticated-orcid":false,"family":"Yunjiong Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.bspc.2026.110342_b1","doi-asserted-by":"crossref","first-page":"525","DOI":"10.3390\/brainsci15050525","article-title":"Physical, cognitive, social, and functional health correlates of major depressive disorder subtypes: A systematic review","volume":"15","author":"McKeough","year":"2025","journal-title":"Brain Sci."},{"issue":"1","key":"10.1016\/j.bspc.2026.110342_b2","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1186\/s12888-023-05038-7","article-title":"A factor analytic comparison of three commonly used depression scales (HAMD, MADRS, BDI) in a large sample of depressed inpatients","volume":"23","author":"Seem\u00fcller","year":"2023","journal-title":"BMC Psychiatry"},{"issue":"2","key":"10.1016\/j.bspc.2026.110342_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijchp.2022.100350","article-title":"Criterion and construct validity of the beck depression inventory (BDI-II) to measure depression in patients with cancer: The contribution of somatic items","volume":"23","author":"Almeida","year":"2023","journal-title":"Int. J. Clin. Health Psychol."},{"key":"10.1016\/j.bspc.2026.110342_b4","article-title":"Validated self-administered screening tools to identify depression among young adults (18 to 25-years-old) in east Asia and the Pacific region low-and-middle income countries (LMICs): A systematic review","volume":"23","author":"Dantic","year":"2025","journal-title":"J. Affect. Disord. Rep."},{"key":"10.1016\/j.bspc.2026.110342_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127015","article-title":"A review on speech emotion recognition: A survey, recent advances, challenges, and the influence of noise","volume":"568","author":"George","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.bspc.2026.110342_b6","doi-asserted-by":"crossref","unstructured":"Q. Deng, S. Luz, S. de la Fuente Garcia, An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech, in: Interspeech 2025, Rotterdam, The Netherlands, 2025, pp. 5248\u20135252, http:\/\/dx.doi.org\/10.21437\/Interspeech.2025-1968.","DOI":"10.21437\/Interspeech.2025-1968"},{"key":"10.1016\/j.bspc.2026.110342_b7","series-title":"2023 International Conference on Sustainable Computing and Smart Systems","first-page":"808","article-title":"Development of an SVM-based depression detection model using MFCC feature extraction","author":"Maheshwar","year":"2023"},{"issue":"2","key":"10.1016\/j.bspc.2026.110342_b8","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1109\/TAFFC.2019.2944380","article-title":"Investigation of speech landmark patterns for depression detection","volume":"13","author":"Huang","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110342_b9","doi-asserted-by":"crossref","unstructured":"S. Kanoujia, P. Karuppanan, Depression Detection in Speech Using ML and DL Algorithm, in: 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI, vol. 2, Gwalior, India, 2024, pp. 1\u20135, http:\/\/dx.doi.org\/10.1109\/IATMSI60426.2024.10503510.","DOI":"10.1109\/IATMSI60426.2024.10503510"},{"key":"10.1016\/j.bspc.2026.110342_b10","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 Netw."},{"key":"10.1016\/j.bspc.2026.110342_b11","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.bspc.2026.110342_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2024.103106","article-title":"Speechformer-CTC: Sequential modeling of depression detection with speech temporal classification","volume":"163","author":"Wang","year":"2024","journal-title":"Speech Commun."},{"key":"10.1016\/j.bspc.2026.110342_b13","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1109\/TNSRE.2022.3224135","article-title":"TAMFN: Time-aware attention multimodal fusion network for depression detection","volume":"31","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"10.1016\/j.bspc.2026.110342_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105898","article-title":"A deep learning model for depression detection based on MFCC and CNN generated spectrogram features","volume":"90","author":"Das","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"issue":"2","key":"10.1016\/j.bspc.2026.110342_b15","doi-asserted-by":"crossref","first-page":"328","DOI":"10.3390\/electronics12020328","article-title":"Depression detection in speech using transformer and parallel convolutional neural networks","volume":"12","author":"Yin","year":"2023","journal-title":"Electronics"},{"key":"10.1016\/j.bspc.2026.110342_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.nexus.2023.100210","article-title":"China mainland new energy index price forecasting with the neural network","volume":"10","author":"Xu","year":"2023","journal-title":"Energy Nexus"},{"key":"10.1016\/j.bspc.2026.110342_b17","article-title":"Depression detection from speech signals using a multiple temporal-frequency scale channel attention mechanism","volume":"113","author":"Wang","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.bspc.2026.110342_b18","doi-asserted-by":"crossref","unstructured":"J. Gratch, R. Artstein, G.M. Lucas, G. Stratou, S. Scherer, A. Nazarian, R. Wood, J. Boberg, D. DeVault, S. Marsella, D. Traum, S. Rizzo, L.-P. Morency, The Distress Analysis Interview Corpus of Human and Computer Interviews, in: Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC, Reykjavik, Iceland, 2014, pp. 3123\u20133128, URL http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/508_Paper.pdf. Available at ACL Anthology.","DOI":"10.63317\/3o7bccg9xequ"},{"issue":"1","key":"10.1016\/j.bspc.2026.110342_b19","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":"Sci. Data"},{"issue":"4","key":"10.1016\/j.bspc.2026.110342_b20","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":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110342_b21","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1016\/j.procs.2023.01.163","article-title":"Speech emotion classification using ensemble models with MFCC","volume":"218","author":"Mohan","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.bspc.2026.110342_b22","series-title":"Optimization, Learning Algorithms and Applications","first-page":"389","article-title":"F0, lpc, and mfcc analysis for emotion recognition based on speech","author":"Teixeira","year":"2022"},{"key":"10.1016\/j.bspc.2026.110342_b23","series-title":"Current and Future Trends on Intelligent Technology Adoption: Volume 1","first-page":"345","article-title":"Understanding the use of acoustic measurement and mel frequency cepstral coefficient (MFCC) features for the classification of depression speech","author":"Shanmugam","year":"2023"},{"key":"10.1016\/j.bspc.2026.110342_b24","article-title":"Acoustic-based machine learning approaches for depression detection in Chinese university students","volume":"13","author":"Wei","year":"2025","journal-title":"Front. Public Health"},{"issue":"1","key":"10.1016\/j.bspc.2026.110342_b25","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1186\/s12888-024-06253-6","article-title":"The voice of depression: speech features as biomarkers for major depressive disorder","volume":"24","author":"Menne","year":"2024","journal-title":"BMC Psychiatry"},{"key":"10.1016\/j.bspc.2026.110342_b26","series-title":"2018 Chinese Automation Congress","first-page":"2705","article-title":"Improvement on speech depression recognition based on deep networks","author":"Li","year":"2018"},{"key":"10.1016\/j.bspc.2026.110342_b27","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.jad.2022.11.060","article-title":"Depression recognition using a proposed speech chain model fusing speech production and perception features","volume":"323","author":"Du","year":"2023","journal-title":"J. Affect. Disord."},{"key":"10.1016\/j.bspc.2026.110342_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116076","article-title":"Audio based depression detection using convolutional autoencoder","volume":"189","author":"Sardari","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"4","key":"10.1016\/j.bspc.2026.110342_b29","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1109\/TAFFC.2025.3565654","article-title":"Examining the fourier spectrum of speech signal from a time-frequency perspective for automatic depression level prediction","volume":"16","author":"Niu","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110342_b30","doi-asserted-by":"crossref","unstructured":"K. Feng, T. Chaspari, A Knowledge-Driven Vowel-Based Approach of Depression Classification from Speech Using Data Augmentation, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Rhodes Island, Greece, 2023, pp. 1\u20135, http:\/\/dx.doi.org\/10.1109\/ICASSP49357.2023.10096105.","DOI":"10.1109\/ICASSP49357.2023.10096105"},{"key":"10.1016\/j.bspc.2026.110342_b31","article-title":"A hybrid model for depression detection using deep learning","volume":"25","author":"Vandana","year":"2023","journal-title":"Meas.: Sensors"},{"issue":"02","key":"10.1016\/j.bspc.2026.110342_b32","doi-asserted-by":"crossref","DOI":"10.1142\/S0218213023400043","article-title":"An effective depression diagnostic system using speech signal analysis through deep learning methods","volume":"32","author":"Verma","year":"2023","journal-title":"Int. J. Artif. Intell. Tools"},{"issue":"3","key":"10.1016\/j.bspc.2026.110342_b33","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1109\/TAFFC.2022.3154332","article-title":"Prediction of depression severity based on the prosodic and semantic features with bidirectional LSTM and time distributed CNN","volume":"14","author":"Mao","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.bspc.2026.110342_b34","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6247","article-title":"Automatic depression detection: An emotional audio-textual corpus and a gru\/bilstm-based model","author":"Shen","year":"2022"},{"key":"10.1016\/j.bspc.2026.110342_b35","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS)","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.bspc.2026.110342_b36","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Multi-local attention for speech-based depression detection","author":"Tao","year":"2023"},{"key":"10.1016\/j.bspc.2026.110342_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.jad.2025.121077","article-title":"Depression detection from speech data using deep learning\u2013based optimized temporal\u2013frequency\u2013channel attention with interpretable acoustic\u2013prosodic mapping","volume":"399","author":"Rezaee","year":"2026","journal-title":"J. Affect. Disord."},{"key":"10.1016\/j.bspc.2026.110342_b38","article-title":"An integrated vector error correction and directed acyclic graph method for investigating contemporaneous causalities","volume":"7","author":"Xu","year":"2023","journal-title":"Decis. Anal. J."},{"key":"10.1016\/j.bspc.2026.110342_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106870","article-title":"Price forecasts of ten steel products using Gaussian process regressions","volume":"126","author":"Xu","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.bspc.2026.110342_b40","article-title":"Individual time series and composite forecasting of the Chinese stock index","volume":"5","author":"Xu","year":"2021","journal-title":"Mach. Learn. Appl."},{"key":"10.1016\/j.bspc.2026.110342_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2021.106120","article-title":"Corn cash price forecasting with neural networks","volume":"184","author":"Xu","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.bspc.2026.110342_b42","doi-asserted-by":"crossref","unstructured":"X. Ma, X. Dai, Y. Bai, Y. Wang, Y. Fu, Rewrite the Stars, in: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, Seattle, WA, USA, 2024, pp. 5694\u20135703, http:\/\/dx.doi.org\/10.1109\/CVPR52733.2024.00544.","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"10.1016\/j.bspc.2026.110342_b43","series-title":"Advances in Neural Information Processing Systems","first-page":"92381","article-title":"Infinite-dimensional feature interaction","volume":"vol. 37","author":"Xu","year":"2024"},{"key":"10.1016\/j.bspc.2026.110342_b44","doi-asserted-by":"crossref","unstructured":"Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, S. Xie, A ConvNet for the 2020s, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, New Orleans, USA, 2022, pp. 11976\u201311986, http:\/\/dx.doi.org\/10.1109\/CVPR52688.2022.01167.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.bspc.2026.110342_b45","series-title":"Advances in Neural Information Processing Systems","first-page":"10353","article-title":"HorNet: Efficient high-order spatial interactions with recursive gated convolutions","volume":"vol. 35","author":"Rao","year":"2022"},{"key":"10.1016\/j.bspc.2026.110342_b46","doi-asserted-by":"crossref","unstructured":"X. Ding, X. Zhang, J. Han, G. Ding, Scaling Up Your Kernels to 31 \u00d7 31: Revisiting Large Kernel Design in CNNs, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, New Orleans, LA, USA, 2022, pp. 11963\u201311975, http:\/\/dx.doi.org\/10.1109\/CVPR52688.2022.01166.","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"10.1016\/j.bspc.2026.110342_b47","series-title":"Image and Graphics","first-page":"106","article-title":"Learn to enhance the negative information in convolutional neural network","author":"Cai","year":"2023"},{"key":"10.1016\/j.bspc.2026.110342_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106968","article-title":"MSFT: A multi-scale feature-based transformer model for arrhythmia classification","volume":"100","author":"Zhang","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"issue":"1","key":"10.1016\/j.bspc.2026.110342_b49","doi-asserted-by":"crossref","first-page":"12734","DOI":"10.1038\/s41598-024-63556-0","article-title":"Depression recognition using voice-based pre-training model","volume":"14","author":"Huang","year":"2024","journal-title":"Sci. Rep."},{"issue":"12","key":"10.1016\/j.bspc.2026.110342_b50","doi-asserted-by":"crossref","first-page":"13601","DOI":"10.1007\/s11227-023-05207-1","article-title":"Regional steel price index forecasts with neural networks: evidence from east, south, north, central south, northeast, southwest, and northwest China","volume":"79","author":"Xu","year":"2023","journal-title":"J. Supercomput."},{"key":"10.1016\/j.bspc.2026.110342_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.nexus.2023.100250","article-title":"Edible oil wholesale price forecasts via the neural network","volume":"12","author":"Xu","year":"2023","journal-title":"Energy Nexus"},{"key":"10.1016\/j.bspc.2026.110342_b52","series-title":"Computer Vision \u2013 ECCV 2022 Workshops","first-page":"623","article-title":"Multi-modal depression estimation based on sub-attentional fusion","author":"Wei","year":"2023"},{"issue":"6","key":"10.1016\/j.bspc.2026.110342_b53","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 J. Sel. Top. Signal Process."},{"key":"10.1016\/j.bspc.2026.110342_b54","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 Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.bspc.2026.110342_b55","doi-asserted-by":"crossref","first-page":"9543","DOI":"10.1038\/s41598-024-60278-1","article-title":"Improving speech depression detection using transfer learning with wav2vec 2.0 in low-resource environments","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426008967?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426008967?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T06:11:24Z","timestamp":1778825484000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426008967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":55,"alternative-id":["S1746809426008967"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110342","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A model for speech depression detection based on star operation and relative position encoding","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110342","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":"110342"}}