{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T03:20:48Z","timestamp":1773717648312,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_12","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:21Z","timestamp":1760253561000},"page":"173-187","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Investigation of Explainable Multimodal Methods for Detecting Mental Disorders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-2330","authenticated-orcid":false,"given":"Mikhail","family":"Dolgushin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1753-9904","authenticated-orcid":false,"given":"Daria","family":"Guseva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3424-652X","authenticated-orcid":false,"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","first-page":"184487","DOI":"10.1109\/ACCESS.2024.3506433","volume":"12","author":"C Botelho","year":"2024","unstructured":"Botelho, C., Abad, A., Schultz, T., Trancoso, I.: Speech as a biomarker for disease detection. IEEE Access 12, 184487\u2013184508 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3506433","journal-title":"IEEE Access"},{"key":"12_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106433","volume":"211","author":"M Muzammel","year":"2021","unstructured":"Muzammel, M., Salam, H., Othmani, A.: End-to-end multimodal clinical depression recognition using deep neural networks: a comparative analysis. Comput. Methods Programs Biomed. 211, 106433 (2021). https:\/\/doi.org\/10.1016\/j.cmpb.2021.106433","journal-title":"Comput. Methods Programs Biomed."},{"key":"12_CR3","doi-asserted-by":"publisher","unstructured":"Monferrer, M., Garc\u00eda, A.S., Ricarte, J.J., et al.: Facial emotion recognition in patients with depression compared to healthy controls when using human avatars. Scientific Reports 13, 6007 (2023). https:\/\/doi.org\/10.1038\/s41598-023-31277-5","DOI":"10.1038\/s41598-023-31277-5"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Barrera-Altuna, B., Lee, D., Zarnaz, Z., Han, J., Kim, S.: The interspeech 2024 TAUKADIAL challenge: multilingual mild cognitive impairment detection with multimodal approach. In: Proc. Interspeech 2024, pp. 967\u2013971 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-1352","DOI":"10.21437\/Interspeech.2024-1352"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Favaro, A., Cao, T., Dehak, N., Moro-Velazquez, L.: Leveraging universal speech representations for detecting and assessing the severity of mild cognitive impairment across languages. In: Proc. Interspeech 2024, pp. 972\u2013976 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-2030","DOI":"10.21437\/Interspeech.2024-2030"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Gosztolya, G., T\u00f3th, L.: Combining acoustic feature sets for detecting mild cognitive impairment in the interspeech'24 TAUKADIAL Challenge. In: Proc. Interspeech 2024, pp. 957\u2013961 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-984","DOI":"10.21437\/Interspeech.2024-984"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Yu, J., Kaya, H.: Using emotionally rich speech segments for depression prediction. In: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10889722"},{"issue":"2","key":"12_CR8","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1109\/TAFFC.2020.2973984","volume":"13","author":"HJ Escalante","year":"2022","unstructured":"Escalante, H.J., et al.: Modeling, recognizing, and explaining apparent personality from videos. IEEE Trans. Affect. Comput. 13(2), 894\u2013911 (2022). https:\/\/doi.org\/10.1109\/TAFFC.2020.2973984","journal-title":"IEEE Trans. Affect. Comput."},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/s00530-025-01690-z","volume":"31","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Zhu, W., Dong, L., et al.: Enhancing interpretability in video-based personality trait recognition using SHAP analysis. Multimedia Syst. 31, 150 (2025). https:\/\/doi.org\/10.1007\/s00530-025-01690-z","journal-title":"Multimedia Syst."},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Lim, W.S., Chiu, SI., Wu, MC., et al.: An integrated biometric voice and facial features for early detection of Parkinson\u2019s disease. npj Parkinson's Disease 8, 145 (2022). https:\/\/doi.org\/10.1038\/s41531-022-00414-8","DOI":"10.1038\/s41531-022-00414-8"},{"key":"12_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106480","volume":"95","author":"C Lv","year":"2024","unstructured":"Lv, C., et al.: Leveraging multimodal deep learning framework and a comprehensive audio-visual dataset to advance Parkinson\u2019s detection. Biomed. Signal Process. Control 95, 106480 (2024). https:\/\/doi.org\/10.1016\/j.bspc.2024.106480","journal-title":"Biomed. Signal Process. Control"},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Correia, J., et al.: The in-the-wild speech medical corpus. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6973\u20136977 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414230","DOI":"10.1109\/ICASSP39728.2021.9414230"},{"key":"12_CR13","doi-asserted-by":"publisher","unstructured":"Zhou, A., et al.: YouTubePD: a multimodal benchmark for Parkinson\u2019s disease analysis. In: Advances in Neural Information Processing Systems, vol. 36, pp. 55140\u201355159 (2023). https:\/\/doi.org\/10.5555\/3666122.3668530","DOI":"10.5555\/3666122.3668530"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Dodge, H.H., et al: Internet-based conversational engagement randomized controlled clinical trial (I-CONECT) among socially isolated adults 75+ years old with normal cognition or MCI: topline results. Gerontologist 64(5) (2023). https:\/\/doi.org\/10.1093\/geront\/gnad147","DOI":"10.1093\/geront\/gnad147"},{"key":"12_CR15","unstructured":"Mu, X., et al.: Detecting Cognitive Impairment and Psychological Well-being among Older Adults Using Facial, Acoustic, Linguistic, and Cardiovascular Patterns Derived from Remote Conversations. arXiv preprint. arXiv:2412.14194 (2024). https:\/\/arxiv.org\/abs\/2412.14194"},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Radford, A., et al.: Robust speech recognition via large-scale weak supervision. In: International conference on machine learning, pp. 28492\u201328518 (2023). https:\/\/doi.org\/10.5555\/3618408.3619590","DOI":"10.5555\/3618408.3619590"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Shivkumar, A., Weston, J., Lenain, R., Fristed, E.: BlaBla: linguistic feature extraction for clinical analysis in multiple languages. In: Proc. Interspeech 2020, pp. 2542\u20132546 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2880","DOI":"10.21437\/Interspeech.2020-2880"},{"issue":"12","key":"12_CR18","doi-asserted-by":"publisher","first-page":"3529","DOI":"10.3390\/s20123529","volume":"20","author":"L di Biase","year":"2020","unstructured":"di Biase, L.: Gait analysis in Parkinson\u2019s disease: an overview of the most accurate markers for diagnosis and symptoms monitoring. Sensors. 20(12), 3529 (2020). https:\/\/doi.org\/10.3390\/s20123529","journal-title":"Sensors."},{"key":"12_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122441","volume":"239","author":"E Ryumina","year":"2024","unstructured":"Ryumina, E., et al.: OCEAN-AI framework with EmoFormer cross-hemiface attention approach for personality traits assessment. Expert Syst. Appl. 239, 122441 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2023.122441","journal-title":"Expert Syst. Appl."},{"key":"12_CR20","unstructured":"Ryumina, E., Ryumin, D., Karpov, A.: OCEAN-AI: open multimodal framework for personality traits assessment and HR-processes automatization. In: Proc. Interspeech 2024, pp. 3630\u20133631 (2024). https:\/\/www.isca-archive.org\/interspeech_2024\/ryumina24_interspeech.html"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Ekman, P.: Basic emotions. Handbook of Cognition and Emotion, pp. 4\u20135 (1999)","DOI":"10.1002\/0470013494.ch3"},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Lundberg, S.M., Lee, S.I. A unified approach to interpreting model predictions. In: Advances in neural information processing systems, vol. 30, pp. 4768\u20134777 (2017). https:\/\/doi.org\/10.5555\/3295222.3295230","DOI":"10.5555\/3295222.3295230"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, vol. 30, pp. 6000\u20136010 (2017). https:\/\/doi.org\/10.5555\/3295222.3295349","DOI":"10.5555\/3295222.3295349"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:24Z","timestamp":1760253564000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}