{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T13:17:24Z","timestamp":1783516644068,"version":"3.55.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Neurodyn"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s11571-026-10500-9","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T12:40:59Z","timestamp":1783514459000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech-based depression detection using higher-order spectral features and a multi-level transformer"],"prefix":"10.1007","volume":"20","author":[{"given":"Uma","family":"Jaishankar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jagannath H.","family":"Nirmal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"10500_CR1","first-page":"181","volume-title":"International conference on wireless, intelligent, and distributed environment for communication: WIDECOM 2018","author":"G Agarwal","year":"2018","unstructured":"Agarwal G, Maheshkar V, Maheshkar S, Gupta S (2018) Recognition of emotions of speech and mood of music: a review. International conference on wireless, intelligent, and distributed environment for communication: WIDECOM 2018. Springer, Berlin, pp 181\u2013197"},{"issue":"8","key":"10500_CR2","doi-asserted-by":"publisher","first-page":"1835","DOI":"10.1002\/acs.3425","volume":"36","author":"G Agarwal","year":"2022","unstructured":"Agarwal G, Om H, Gupta S (2022) A learning framework of modified deep recurrent neural network for classification and recognition of voice mood. Int J Adapt Control Signal Process 36(8):1835\u20131859","journal-title":"Int J Adapt Control Signal Process"},{"key":"10500_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2020.3035535","author":"SM Alghowinem","year":"2020","unstructured":"Alghowinem SM, Gedeon T, Goecke R, Cohn J, Parker G (2020) Interpretation of depression detection models via feature selection methods. IEEE Trans Affect Comput. https:\/\/doi.org\/10.1109\/taffc.2020.3035535","journal-title":"IEEE Trans Affect Comput"},{"key":"10500_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2026.104462","author":"AA Alhussan","year":"2026","unstructured":"Alhussan AA, El-Kenawy ES, Eid MM, Khodadadi N (2026) Hybrid Al-Biruni and puma optimization (BERPO) for boosting the classification of quality-of-service (QoS) in 5G networks. J Netw Comput Appl. https:\/\/doi.org\/10.1016\/j.jnca.2026.104462","journal-title":"J Netw Comput Appl"},{"issue":"1","key":"10500_CR5","doi-asserted-by":"publisher","first-page":"25560","DOI":"10.1038\/s41598-025-09414-z","volume":"15","author":"A Atta","year":"2025","unstructured":"Atta A, ElSayad D, Ezzat D, Amin S, ElGamal M (2025) Efficacy of swarm-based neural networks in automated depression detection. Sci Rep 15(1):25560","journal-title":"Sci Rep"},{"key":"10500_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15132-3","author":"A Bastanfard","year":"2023","unstructured":"Bastanfard A, Abbasian A (2023) Speech emotion recognition in Persian based on stacked autoencoder by comparing local and global features. Multim Tools Appl. https:\/\/doi.org\/10.1007\/s11042-023-15132-3","journal-title":"Multim Tools Appl"},{"issue":"2","key":"10500_CR7","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1109\/JSTSP.2019.2908696","volume":"13","author":"E Bavu","year":"2019","unstructured":"Bavu E, Ramamonjy A, Pujol H, Garcia A (2019) TimeScaleNet: A multiresolution approach for raw audio recognition using learnable biquadratic IIR filters and residual networks of depthwise-separable one-dimensional atrous convolutions. IEEE Journal of Selected Topics in Signal Processing 13(2):220\u2013235","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10500_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2025.3574864","author":"X Chen","year":"2025","unstructured":"Chen X, Shao Z, Jiang Y, Chen R, Wang Y, Li B, Niu M, Chen H, Hu Q, Wu J, Yang C (2025) TTFNet: temporal-frequency features fusion network for speech based automatic depression recognition and assessment. IEEE J Biomed Health Inform. https:\/\/doi.org\/10.1109\/jbhi.2025.3574864","journal-title":"IEEE J Biomed Health Inform"},{"key":"10500_CR9","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1016\/j.procs.2019.12.228","volume":"164","author":"K Chlasta","year":"2019","unstructured":"Chlasta K, Wo\u0142k K, Krejtz I (2019) Automated speech-based screening of depression using deep convolutional neural networks. Procedia Comput Sci 164:618\u2013628","journal-title":"Procedia Comput Sci"},{"key":"10500_CR10","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/TAFFC.2021.3072579","volume":"14","author":"WC de Melo","year":"2021","unstructured":"de Melo WC, Granger E, Lopez MB (2021) MDN: A deep maximization-differentiation network for spatio-temporal depression detection. IEEE Trans Affect Comput 14:578\u2013590","journal-title":"IEEE Trans Affect Comput"},{"key":"10500_CR11","unstructured":"Deshpande D, Sharma K, Gupta SK. (2025) Deep acoustic profiling using CNNs for early detection of depression: integrating neural networks with mental health screening. SGS-Engineering & Sciences. 1(2)."},{"key":"10500_CR12","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.jad.2021.04.004","volume":"288","author":"Y Di","year":"2021","unstructured":"Di Y, Wang J, Li W, Zhu T (2021) Using i-vectors from voice features to identify major depressive disorder. J Affect Disord 288:161\u2013166","journal-title":"J Affect Disord"},{"key":"10500_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2024.1430035","volume":"12","author":"H Ding","year":"2024","unstructured":"Ding H, Du Z, Wang Z, Xue J, Wei Z, Yang K, Jin S, Zhang Z, Wang J (2024) IntervoxNet: a novel dual-modal audio-text fusion network for automatic and efficient depression detection from interviews. Front Phys 12:1430035. https:\/\/doi.org\/10.3389\/fphy.2024.1430035","journal-title":"Front Phys"},{"key":"10500_CR14","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.neucom.2021.02.019","volume":"441","author":"Y Dong","year":"2021","unstructured":"Dong Y, Yang X (2021) A hierarchical depression detection model based on vocal and emotional cues. Neurocomputing 441:279\u2013290","journal-title":"Neurocomputing"},{"key":"10500_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-025-10647-3","author":"ES El-Kenawy","year":"2025","unstructured":"El-Kenawy ES, Ibrahim A, Alhussan AA, Khafaga DS, Ahmed AE, Eid MM (2025) Smart city electricity load forecasting using greylag goose optimization-enhanced time series analysis. Arab J Sci Eng. https:\/\/doi.org\/10.1007\/s13369-025-10647-3","journal-title":"Arab J Sci Eng"},{"issue":"3","key":"10500_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-026-11504-x","volume":"59","author":"ES El-kenawy","year":"2026","unstructured":"El-kenawy ES, Khodadadi N, Mirjalili S, Zaki AM, Ibrahim A, Alhussan AA, Khafaga DS, Eid MM (2026) Glider snake optimizer (GSO): a nature-inspired metaheuristic algorithm for global and engineering optimization problems. Artif Intell Rev 59(3):91. https:\/\/doi.org\/10.1007\/s10462-026-11504-x","journal-title":"Artif Intell Rev"},{"issue":"5","key":"10500_CR17","doi-asserted-by":"publisher","first-page":"3632","DOI":"10.1109\/JBHI.2025.3529348","volume":"29","author":"R Flores","year":"2025","unstructured":"Flores R, Tlachac ML, Shrestha A, Rundensteiner EA (2025) WavFace: a multimodal transformer-based model for depression screening. IEEE J Biomed Health Inform 29(5):3632\u20133641","journal-title":"IEEE J Biomed Health Inform"},{"key":"10500_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.mex.2024.102976","volume":"13","author":"D Ghosh","year":"2024","unstructured":"Ghosh D, Karande H, Gite S, Pradhan B (2024) Psychological disorder detection: a multimodal approach using a transformer-based hybrid model. MethodsX 13:102976","journal-title":"MethodsX"},{"key":"10500_CR19","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.neucom.2020.10.015","volume":"422","author":"L He","year":"2021","unstructured":"He L, Chan JC, Wang Z (2021) Automatic depression recognition using CNN with attention mechanism from videos. Neurocomputing 422:165\u2013175","journal-title":"Neurocomputing"},{"key":"10500_CR20","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.inffus.2021.10.012","volume":"80","author":"L He","year":"2022","unstructured":"He L, Niu M, Tiwari P, Marttinen P, Su R, Jiang J, Guo C, Wang H, Ding S, Wang Z, Pan X (2022) Deep learning for depression recognition with audiovisual cues: A review. Information Fusion 80:56\u201386","journal-title":"Information Fusion"},{"key":"10500_CR21","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1109\/ICMLA61862.2024.00213","volume-title":"2024 International conference on machine learning and applications (ICMLA)","author":"J Hong","year":"2024","unstructured":"Hong J, Lee J, Cho D, Jung J (2024) Depression classification algorithm based on voice signals using MFCC and CNN autoencoders. 2024 International conference on machine learning and applications (ICMLA). IEEE, New York City, pp 1368\u20131373"},{"issue":"2","key":"10500_CR22","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/TAFFC.2019.2944380","volume":"13","author":"Z Huang","year":"2019","unstructured":"Huang Z, Epps J, Joachim D (2019) Investigation of speech landmark patterns for depression detection. IEEE Trans Affect Comput 13(2):666\u2013679","journal-title":"IEEE Trans Affect Comput"},{"issue":"3","key":"10500_CR23","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/TCDS.2017.2721552","volume":"10","author":"A Jan","year":"2017","unstructured":"Jan A, Meng H, Gaus YF, Zhang F (2017) Artificial intelligent system for automatic depression level analysis through visual and vocal expressions. IEEE Transactions on Cognitive and Developmental Systems 10(3):668\u2013680","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"1","key":"10500_CR24","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/s13278-024-01360-4","volume":"14","author":"M Kerasiotis","year":"2024","unstructured":"Kerasiotis M, Ilias L, Askounis D (2024) Depression detection in social media posts using transformer-based models and auxiliary features. Soc Netw Anal Min 14(1):196","journal-title":"Soc Netw Anal Min"},{"issue":"11","key":"10500_CR25","doi-asserted-by":"publisher","first-page":"2204","DOI":"10.1109\/TASLP.2018.2858923","volume":"26","author":"Y Kim","year":"2018","unstructured":"Kim Y, Kim M, Goo J, Kim H (2018) Learning self-informed feature contribution for deep learning-based acoustic modeling. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 26(11):2204\u20132214","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"10500_CR26","doi-asserted-by":"publisher","DOI":"10.1111\/coin.70019","volume":"41","author":"Y Kou","year":"2025","unstructured":"Kou Y, Ge F, Chen D, Shen L, Liu H (2025) An enhanced cross\u2010attention based multimodal model for depression detection. Comput Intell 41(1):e70019","journal-title":"Comput Intell"},{"key":"10500_CR27","first-page":"3946","volume-title":"ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"G Lam","year":"2019","unstructured":"Lam G, Dongyan H, Lin W (2019) Context-aware deep learning for multi-modal depression detection. ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, New York City, pp 3946\u20133950"},{"key":"10500_CR28","doi-asserted-by":"crossref","unstructured":"Li Y, Zhao T, Kawahara T. (2019) Improved end-to-end speech emotion recognition using self attention mechanism and multitask learning. In Interspeech 2803\u20132807.","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"10500_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114683","volume":"173","author":"D Li","year":"2021","unstructured":"Li D, Liu J, Yang Z, Sun L, Wang Z (2021) Speech emotion recognition using recurrent neural networks with directional self-attention. Expert Syst Appl 173:114683","journal-title":"Expert Syst Appl"},{"key":"10500_CR30","doi-asserted-by":"crossref","unstructured":"Ma X, Yang H, Chen Q, Huang D, Wang Y. (2016) Depaudionet: an efficient deep model for audio based depression classification. In Proceedings of the 6th international workshop on audio\/visual emotion challenge. 35\u201342.","DOI":"10.1145\/2988257.2988267"},{"key":"10500_CR100","doi-asserted-by":"crossref","unstructured":"Meurs, Marie-Jean, and Frank Rudzicz, eds. (2019) Advances in Artificial Intelligence: 32nd Canadian Conference on Artificial Intelligence, Canadian AI 2019, Kingston, ON, Canada, May 28\u201331, Proceedings. Vol. 11489. Springer, 2019.","DOI":"10.1007\/978-3-030-18305-9"},{"key":"10500_CR31","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.specom.2022.07.006","volume":"143","author":"X Miao","year":"2022","unstructured":"Miao X, Li Y, Wen M, Liu Y, Julian IN, Guo H (2022) Fusing features of speech for depression classification based on higher-order spectral analysis. Speech Commun 143:46\u201356","journal-title":"Speech Commun"},{"key":"10500_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2020.100005","volume":"2","author":"M Muzammel","year":"2020","unstructured":"Muzammel M, Salam H, Hoffmann Y, Chetouani M, Othmani A (2020) AudVowelConsNet: A phoneme-level based deep CNN architecture for clinical depression diagnosis. Machine Learning with Applications 2:100005","journal-title":"Machine Learning with Applications"},{"key":"10500_CR33","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1109\/TAFFC.2020.3031345","volume":"14","author":"M Niu","year":"2020","unstructured":"Niu M, Tao J, Liu B, Huang J, Lian Z (2020) Multimodal spatiotemporal representation for automatic depression level detection. IEEE Trans Affect Comput 14:294\u2013307","journal-title":"IEEE Trans Affect Comput"},{"key":"10500_CR34","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","volume":"42","author":"K Noda","year":"2015","unstructured":"Noda K, Yamaguchi Y, Nakadai K, Okuno HG, Ogata T (2015) Audio-visual speech recognition using deep learning. Appl Intell 42:722\u2013737","journal-title":"Appl Intell"},{"key":"10500_CR35","doi-asserted-by":"crossref","unstructured":"Othmani A, Kadoch D, Bentounes K, Rejaibi E, Alfred R, Hadid A. (2021) Towards robust deep neural networks for affect and depression recognition from speech. In Pattern recognition. ICPR international workshops and challenges: virtual event, January 10\u201315, 2021, Proceedings, Part II. Springer International Publishing. 5\u201319","DOI":"10.1007\/978-3-030-68790-8_1"},{"issue":"4","key":"10500_CR36","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1109\/TAFFC.2017.2724035","volume":"10","author":"A Pampouchidou","year":"2017","unstructured":"Pampouchidou A, Simos PG, Marias K, Meriaudeau F, Yang F, Pediaditis M, Tsiknakis M (2017) Automatic assessment of depression based on visual cues: a systematic review. IEEE Trans Affect Comput 10(4):445\u2013470","journal-title":"IEEE Trans Affect Comput"},{"key":"10500_CR37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-026-39632-y","author":"M Radwan","year":"2026","unstructured":"Radwan M, Ibrahim A, Abdelsalam MM, Alhussan AA, Mattar EA, El-Kenawy ES (2026) Optimizing solar and wind forecasting with iHow optimization algorithm and multi-scale attention networks: M. Radwan et al. Sci Rep. https:\/\/doi.org\/10.1038\/s41598-026-39632-y","journal-title":"Sci Rep"},{"key":"10500_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101605","volume":"86","author":"V Ravi","year":"2024","unstructured":"Ravi V, Wang J, Flint J, Alwan A (2024) Enhancing accuracy and privacy in speech-based depression detection through speaker disentanglement. Comput Speech Lang 86:101605","journal-title":"Comput Speech Lang"},{"key":"10500_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103107","volume":"71","author":"E Rejaibi","year":"2022","unstructured":"Rejaibi E, Komaty A, Meriaudeau F, Agrebi S, Othmani A (2022a) MFCC-based recurrent neural network for automatic clinical depression recognition and assessment from speech. Biomed Signal Process Control 71:103107","journal-title":"Biomed Signal Process Control"},{"issue":"4","key":"10500_CR40","first-page":"6460","volume":"16","author":"MA Saeed","year":"2025","unstructured":"Saeed MA, Komashinsky V, Mohammed SA, Abdulqader NN, Saif LQ (2025) Speech signal analysis to predict depression. Int J Adv Netw Appl 16(4):6460\u20136465","journal-title":"Int J Adv Netw Appl"},{"key":"10500_CR41","doi-asserted-by":"crossref","unstructured":"Saidi A, Othman SB, Saoud SB. (2020) Hybrid CNN-SVM classifier for efficient depression detection system. In 2020 4th International Conference on Advanced Systems and Emergent Technologies (IC_ASET). IEEE. 229\u2013234","DOI":"10.1109\/IC_ASET49463.2020.9318302"},{"key":"10500_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116076","volume":"189","author":"S Sardari","year":"2022","unstructured":"Sardari S, Nakisa B, Rastgoo MN, Eklund P (2022) Audio based depression detection using Convolutional Autoencoder. Expert Syst Appl 189:116076","journal-title":"Expert Syst Appl"},{"key":"10500_CR43","doi-asserted-by":"publisher","DOI":"10.1109\/tfuzz.2025.3569888","author":"J Shen","year":"2025","unstructured":"Shen J, Wu J, Zhang Y, Zhu K, Wang K, Hu W, Hou K, Qian K, Zhang X, Hu B (2025a) MF $^{2} $-Net: exploring a meta-fuzzy multimodal fusion network for depression recognition. IEEE Trans Fuzzy Syst. https:\/\/doi.org\/10.1109\/tfuzz.2025.3569888","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"10500_CR44","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3646189","author":"J Shen","year":"2025","unstructured":"Shen J, Wang K, Zhao Z, Zhang Y, Tian F, Zhang X, Dong Q, Hu B (2025b) WDANet: Wasserstein distribution inspired dynamic adversarial network for EEG-based cross-domain depression recognition. IEEE Trans Affect Comput. https:\/\/doi.org\/10.1109\/taffc.2025.3646189","journal-title":"IEEE Trans Affect Comput"},{"key":"10500_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103772","author":"J Shen","year":"2025","unstructured":"Shen J, Zhu K, Ma R, Hu W, Tan X, Deng N, Zhou X, Liu Y, Li C, Xu W, Xu C (2025c) Emosavior: depression recognition and intervention via multimodal physiological signals and large language models. Inf Fusion. https:\/\/doi.org\/10.1016\/j.inffus.2025.103772","journal-title":"Inf Fusion"},{"key":"10500_CR46","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3555433","author":"J Shen","year":"2025","unstructured":"Shen J, You L, Ma Y, Zhao Z, Liang H, Zhang Y, Hu B (2025d) Ua-daan: an uncertainty-aware dynamic adversarial adaptation network for EEG-based depression recognition. IEEE Trans Affect Comput. https:\/\/doi.org\/10.1109\/taffc.2025.3555433","journal-title":"IEEE Trans Affect Comput"},{"key":"10500_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2026.104224","author":"J Shen","year":"2026","unstructured":"Shen J, Liang H, Ma R, Xu Y, Zhu K, Gao H, Hou K, Zhang Y, Zhang X, Hu B (2026) Emotion recognition using multimodal physiological signals through regional to global fusion with a spatial-temporal semantic alignment mechanism. Inf Fusion. https:\/\/doi.org\/10.1016\/j.inffus.2026.104224","journal-title":"Inf Fusion"},{"key":"10500_CR48","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-023-00852-4","author":"S Suparatpinyo","year":"2023","unstructured":"Suparatpinyo S, Soonthornphisaj N (2023) Smart voice recognition based on deep learning for depression diagnosis. Artif Life Robot. https:\/\/doi.org\/10.1007\/s10015-023-00852-4","journal-title":"Artif Life Robot"},{"key":"10500_CR49","doi-asserted-by":"crossref","unstructured":"Tasnim M, Stroulia E. (2019) Detecting depression from voice. In Advances in Artificial Intelligence: 32nd Canadian Conference on Artificial Intelligence, Canadian AI 2019, Kingston, ON, Canada, May 28\u201331, 2019, Proceedings 32. Springer International Publishing. 472\u2013478","DOI":"10.1007\/978-3-030-18305-9_47"},{"issue":"6","key":"10500_CR50","doi-asserted-by":"publisher","first-page":"688","DOI":"10.3390\/e22060688","volume":"22","author":"A V\u00e1zquez-Romero","year":"2020","unstructured":"V\u00e1zquez-Romero A, Gallardo-Antol\u00edn A (2020) Automatic detection of depression in speech using ensemble convolutional neural networks. Entropy 22(6):688","journal-title":"Entropy"},{"key":"10500_CR51","doi-asserted-by":"publisher","first-page":"101181","DOI":"10.1109\/ACCESS.2020.2998532","volume":"8","author":"Z Wang","year":"2020","unstructured":"Wang Z, Chen L, Wang L, Diao G (2020) Recognition of audio depression based on convolutional neural network and generative antagonism network model. IEEE Access 8:101181\u2013101191","journal-title":"IEEE Access"},{"key":"10500_CR52","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.csl.2018.08.004","volume":"55","author":"JR Williamson","year":"2019","unstructured":"Williamson JR, Young D, Nierenberg AA, Niemi J, Helfer BS, Quatieri TF (2019) Tracking depression severity from audio and video based on speech articulatory coordination. Comput Speech Lang 55:40\u201356","journal-title":"Comput Speech Lang"},{"key":"10500_CR53","doi-asserted-by":"publisher","first-page":"24033","DOI":"10.1109\/ACCESS.2020.2970496","volume":"8","author":"L Yang","year":"2020","unstructured":"Yang L, Jiang D, Sahli H (2020) Feature augmenting networks for improving depression severity estimation from speech signals. IEEE Access 8:24033\u201324045","journal-title":"IEEE Access"},{"key":"10500_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.05.041","author":"W Yang","year":"2023","unstructured":"Yang W, Liu J, Cao P, Zhu R, Wang Y, Liu JK, Wang F, Zhang X (2023) Attention guided learnable time-domain filterbanks for speech depression detection. Neural Netw. https:\/\/doi.org\/10.1016\/j.neunet.2023.05.041","journal-title":"Neural Netw"},{"issue":"2","key":"10500_CR55","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3390\/electronics12020328","volume":"12","author":"F Yin","year":"2023","unstructured":"Yin F, Du J, Xu X, Zhao L (2023) Depression detection in speech using transformer and parallel convolutional neural networks. Electronics 12(2):328","journal-title":"Electronics"},{"key":"10500_CR56","doi-asserted-by":"publisher","first-page":"1579543","DOI":"10.3389\/fpsyt.2025.1579543","volume":"16","author":"G Zhang","year":"2025","unstructured":"Zhang G, Li S (2025) Personalized prediction and intervention for adolescent mental health: multimodal temporal modeling using transformer. Front Psych 16:1579543","journal-title":"Front Psych"},{"issue":"7","key":"10500_CR57","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.3390\/electronics14071464","volume":"14","author":"L Zhang","year":"2025","unstructured":"Zhang L, Zhang S, Zhang X, Zhao Y (2025a) A Multimodal Artificial Intelligence Model for Depression Severity Detection Based on Audio and Video Signals. Electronics 14(7):1464","journal-title":"Electronics"},{"issue":"1","key":"10500_CR58","doi-asserted-by":"publisher","first-page":"6637","DOI":"10.1038\/s41598-025-90117-w","volume":"15","author":"X Zhang","year":"2025","unstructured":"Zhang X, Li C, Chen W, Zheng J, Li F (2025b) Optimizing depression detection in clinical doctor-patient interviews using a multi-instance learning framework. Sci Rep 15(1):6637","journal-title":"Sci Rep"},{"key":"10500_CR101","doi-asserted-by":"crossref","unstructured":"Zhang, Xu, Chenlong Li, Weisi Chen, Jiaxin Zheng, and Feihong Li. (2025) \u201cOptimizing depression detection in clinical doctor-patient interviews using a multi-instance learning framework.\u201d Sci Rep 15, no. 1:6637","DOI":"10.1038\/s41598-025-90117-w"},{"key":"10500_CR59","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2026.3672521","author":"Y Zhang","year":"2026","unstructured":"Zhang Y, Guo C, Zhu K, Hu W, Hu B, Shen J (2026) R2G $^{3} $ net: a novel hierarchical spatial-temporal neural network with a regional-to-global fusion mechanism for multimodal emotion recognition. IEEE Trans Affect Comput. https:\/\/doi.org\/10.1109\/TAFFC.2026.3672521","journal-title":"IEEE Trans Affect Comput"},{"issue":"2","key":"10500_CR60","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/JSTSP.2019.2955012","volume":"14","author":"Z Zhao","year":"2019","unstructured":"Zhao Z, Bao Z, Zhang Z, Deng J, Cummins N, Wang H, Tao J, Schuller B (2019) Automatic assessment of depression from speech via a hierarchical attention transfer network and attention autoencoders. IEEE Journal of Selected Topics in Signal Processing 14(2):423\u2013434","journal-title":"IEEE Journal of Selected Topics in Signal Processing"}],"container-title":["Cognitive Neurodynamics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11571-026-10500-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11571-026-10500-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11571-026-10500-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T12:41:02Z","timestamp":1783514462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11571-026-10500-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["10500"],"URL":"https:\/\/doi.org\/10.1007\/s11571-026-10500-9","relation":{},"ISSN":["1871-4080","1871-4099"],"issn-type":[{"value":"1871-4080","type":"print"},{"value":"1871-4099","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]},"assertion":[{"value":"23 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All the authors involved have agreed to participate in this submitted article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"All the authors involved in this manuscript give full consent for the publication of this submitted article.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"130"}}