{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:03:41Z","timestamp":1786118621324,"version":"build-2736575974"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":89,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Medical Informatics"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.ijmedinf.2025.106208","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T16:34:45Z","timestamp":1764866085000},"page":"106208","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["TransformerCARE: A novel speech analysis pipeline using transformer-based models and audio augmentation techniques for cognitive impairment detection"],"prefix":"10.1016","volume":"207","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4284-9869","authenticated-orcid":false,"given":"Hossein","family":"Azadmaleki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Zolnour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sina","family":"Rashidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0648-6702","authenticated-orcid":false,"given":"James M.","family":"Noble","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Hirschberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elyas","family":"Esmaeili","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tahoura","family":"Morovati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4484-2990","authenticated-orcid":false,"given":"Maryam","family":"Zolnoori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2013","key":"10.1016\/j.ijmedinf.2025.106208_b0005","first-page":"208","article-title":"Alzheimer\u2019s disease facts and figures","volume":"9","author":"Association","year":"2013","journal-title":"Alzheimer\u2019s Dement."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0010","doi-asserted-by":"crossref","first-page":"M621","DOI":"10.1093\/gerona\/59.6.M621","article-title":"Dementia assessment in primary care: results from a study in three managed care systems","volume":"59","author":"Boise","year":"2004","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0015","doi-asserted-by":"crossref","first-page":"130","DOI":"10.2174\/1567205014666171121114930","article-title":"A speech recognition-based solution for the automatic detection of mild cognitive impairment from spontaneous speech","volume":"15","author":"T\u00f3th","year":"2018","journal-title":"Curr. Alzheimer Res."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0020","unstructured":"National Institute on Aging., Assessing Cognitive Impairment in Older Patients, (n.d.). https:\/\/www.nia.nih.gov\/health\/assessing-cognitive-impairment-older-patients (accessed March 1, 2021)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0025","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1080\/13607863.2019.1577799","article-title":"Do people with dementia and mild cognitive impairments experience stigma? A Cross-Cultural Investigation between Italy, Poland and the UK","volume":"24","author":"Lion","year":"2020","journal-title":"Aging Ment. Health"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0030","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1016\/j.neuron.2020.06.004","article-title":"Blood biomarkers: Democratizing alzheimer\u2019s diagnostics","volume":"106","author":"Zetterberg","year":"2020","journal-title":"Neuron"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0035","article-title":"Physician perceptions about the barriers to prompt diagnosis of mild cognitive impairment and Alzheimer\u2019s disease","volume":"2019","author":"Judge","year":"2019","journal-title":"Int. J. Alzheimers Dis."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0040","unstructured":"NationalPlan to AddressAlzheimer\u2019s Disease:2023 Update - Google Scholar, (n.d.). https:\/\/scholar.google.com\/scholar?hl=en&as_sdt=0%2C5&q=NationalPlan+to+AddressAlzheimer%E2%80%99s+Disease%3A2023+Update&btnG= (accessed July 29, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0045","unstructured":"Assessing Cognitive Impairment in Older Patients | National Institute on Aging, (n.d.). https:\/\/www.nia.nih.gov\/health\/health-care-professionals-information\/assessing-cognitive-impairment-older-patients (accessed September 20, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0050","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1097\/TGR.0000000000000001","article-title":"Communication difficulty and relevant interventions in mild cognitive impairment: implications for neuroplasticity","volume":"30","author":"Johnson","year":"2014","journal-title":"Top. Geriatr. Rehabil."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0055","doi-asserted-by":"crossref","first-page":"645","DOI":"10.3389\/fpsyg.2021.620251","article-title":"Ten years of research on automatic voice and speech analysis of people with alzheimer\u2019s disease and mild cognitive impairment: a systematic review article","volume":"12","author":"Mart\u00ednez-Nicol\u00e1s","year":"2021","journal-title":"Front. Psychol."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0060","series-title":"In: Sixteenth Annual Conference of the International Speech Communication Association","article-title":"Automatic detection of mild cognitive impairment from spontaneous speech using ASR","author":"T\u00f3th","year":"2015"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0065","doi-asserted-by":"crossref","DOI":"10.1155\/2020\/4683573","article-title":"Changes in the rhythm of speech difference between people with nondegenerative mild cognitive impairment and with preclinical dementia","volume":"2020","author":"Meil\u00e1n","year":"2020","journal-title":"Behav. Neurol."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0070","unstructured":"models\/research\/audioset\/yamnet at master \u00b7 tensorflow\/models, (n.d.). https:\/\/github.com\/tensorflow\/models\/tree\/master\/research\/audioset\/yamnet (accessed September 20, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0075","doi-asserted-by":"crossref","unstructured":"S. Hershey, S. Chaudhuri, D.P.W. Ellis, J.F. Gemmeke, A. Jansen, R.C. Moore, M. Plakal, D. Platt, R.A. Saurous, B. Seybold, M. Slaney, R.J. Weiss, K. Wilson, CNN Architectures for Large-Scale Audio Classification, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (2016) 131\u2013135. Doi: 10.1109\/ICASSP.2017.7952132.","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0080","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.W. Chang, K. Lee, K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference 1 (2018) 4171\u20134186. https:\/\/arxiv.org\/abs\/1810.04805v2 (accessed August 13, 2024).","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0085","series-title":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 6","first-page":"4211","article-title":"Detecting cognitive decline using speech only: the ADReSSochallenge","author":"Luz","year":"2021"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0090","unstructured":"DementiaBank, (n.d.). https:\/\/talkbank.org\/dementia\/ADReSSo-2021\/index.html (accessed September 18, 2025)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0095","unstructured":"DementiaBank, (n.d.). https:\/\/talkbank.org\/dementia\/ (accessed September 18, 2025)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0100","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0105","unstructured":"A. Baevski, H. Zhou, A. Mohamed, M. Auli, wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations, Adv Neural Inf Process Syst 2020-December (2020). https:\/\/arxiv.org\/abs\/2006.11477v3 (accessed August 13, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0110","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.ijmedinf.2025.106208_b0115","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":"2021","journal-title":"IEEE J. Sel. Top. Sign. Proces."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0120","doi-asserted-by":"crossref","unstructured":"H.J. Chang, S.W. Yang, H.Y. Lee, DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2022-May (2021) 7087\u20137091. Doi: 10.1109\/ICASSP43922.2022.9747490.","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0125","unstructured":"fairseq\/examples\/hubert at main \u00b7 facebookresearch\/fairseq \u00b7 GitHub, (n.d.). https:\/\/github.com\/facebookresearch\/fairseq\/tree\/main\/examples\/hubert (accessed September 22, 2025)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0130","first-page":"597","article-title":"On the computational complexity of self-attention","volume":"201","author":"Keles","year":"2022","journal-title":"Proc. Mach. Learn. Res."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0135","doi-asserted-by":"crossref","DOI":"10.52202\/068431-1189","article-title":"FlashAttention: fast and memory-efficient exact attention with IO-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0140","doi-asserted-by":"crossref","first-page":"176274","DOI":"10.1109\/ACCESS.2020.3026823","article-title":"Multimodal emotion recognition with transformer-based self supervised feature fusion","volume":"8","author":"Siriwardhana","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0145","doi-asserted-by":"crossref","unstructured":"P. Madhyastha, R. Jain, On model stability as a function of random seed, CoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference (2019) 929\u2013939. Doi: 10.18653\/v1\/k19-1087.","DOI":"10.18653\/v1\/K19-1087"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0150","doi-asserted-by":"crossref","DOI":"10.2196\/42792","article-title":"Screening of mild cognitive impairment through conversations with humanoid robots: exploratory pilot study","volume":"7","author":"Yoshii","year":"2023","journal-title":"JMIR Form Res"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0155","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000197","article-title":"Varied performance of picture description task as a screening tool across MCI subtypes","volume":"2","author":"Mefford","year":"2023","journal-title":"PLOS Digital Health"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0160","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/89.759041","article-title":"Improved phase vocoder time-scale modification of audio","volume":"7","author":"Laroche","year":"1999","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0165","doi-asserted-by":"crossref","unstructured":"E. Fonseca, M. Plakal, F. Font, \u2026 D.E. preprint arXiv, undefined 2019, Audio tagging with noisy labels and minimal supervision, Arxiv.OrgE Fonseca, M Plakal, F Font, DPW Ellis, X SerraarXiv Preprint ArXiv:1906.02975, 2019\u2022arxiv.Org (2019). Doi: 10.5281\/zenodo.3612637.","DOI":"10.33682\/w13e-5v06"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0170","doi-asserted-by":"crossref","unstructured":"D.S. Park, W. Chan, Y. Zhang, C.-C. Chiu, B. Zoph, E.D. Cubuk, Q. V. Le, SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2019-September (2019) 2613\u20132617. Doi: 10.21437\/Interspeech.2019-2680.","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0175","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","article-title":"Signal estimation from modified short-time fourier transform","volume":"32","author":"Griffin","year":"1984","journal-title":"IEEE Trans Acoust"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0180","doi-asserted-by":"crossref","unstructured":"B. Puterka, J. Kacur, J. Pavlovicova, Windowing for speech emotion recognition, Proceedings Elmar - International Symposium Electronics in Marine 2019-September (2019) 147\u2013150. Doi: 10.1109\/ELMAR.2019.8918885..","DOI":"10.1109\/ELMAR.2019.8918885"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0185","doi-asserted-by":"crossref","unstructured":"L. Ten Bosch, B. Cranen, A computational model for unsupervised word discovery, International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007 4 (2007) 1481\u20131484. Doi: 10.21437\/INTERSPEECH.2007-429.","DOI":"10.21437\/Interspeech.2007-429"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0190","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1111\/hex.12381","article-title":"Patient communication pattern scale: psychometric characteristics","volume":"19","author":"Ilan","year":"2016","journal-title":"Health Expect."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0195","first-page":"918","article-title":"Machine learning models to predict onset of dementia: a label learning approach","volume":"5","author":"Nori","year":"2019","journal-title":"Alzheimer\u2019s & Dementia : Transl. Res. Clin. Intervent."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0200","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1212\/WNL.0b013e3181a81636","article-title":"Predicting risk of dementia in older adults: the late-life dementia risk index","volume":"73","author":"Barnes","year":"2009","journal-title":"Neurology"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0205","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1016\/S1474-4422(06)70537-3","article-title":"Risk score for the prediction of dementia risk in 20 years among middle aged people: a longitudinal, population-based study","volume":"5","author":"Kivipelto","year":"2006","journal-title":"Lancet Neurol."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0210","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1097\/01.JGP.0000192478.82189.a8","article-title":"Mapping scores onto stages: mini-mental state examination and clinical dementia rating","volume":"14","author":"Perneczky","year":"2006","journal-title":"Am. J. Geriatr. Psychiatry"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0215","unstructured":"F. Eyben, K. Scherer, \u2026 B.S.-I. transactions on, undefined 2015, The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing, Ieeexplore.Ieee.OrgF Eyben, KR Scherer, BW Schuller, J Sundberg, E Andr\u00e9, C Busso, LY Devillers, J EppsIEEE Transactions on Affective Computing, 2015\u2022ieeexplore.Ieee.Org (n.d.). https:\/\/ieeexplore.ieee.org\/abstract\/document\/7160715\/ (accessed August 13, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0220","doi-asserted-by":"crossref","unstructured":"B. Schuller, S. Steidl, A. Batliner, F. Burkhardt, L. Devillers, C. M\u00fcller, S. Narayanan, The INTERSPEECH 2010 paralinguistic challenge, Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (2010) 2794\u20132797. Doi: 10.21437\/INTERSPEECH.2010-739.","DOI":"10.21437\/Interspeech.2010-739"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0225","doi-asserted-by":"crossref","unstructured":"G. Degottex, J. Kane, T. Drugman, T. Raitio, S. Scherer, COVAREP - A collaborative voice analysis repository for speech technologies, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (2014) 960\u2013964. Doi: 10.1109\/ICASSP.2014.6853739.","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0230","doi-asserted-by":"crossref","unstructured":"D. Snyder, D. Garcia-Romero, G. Sell, D. Povey, S. Khudanpur, X-Vectors: Robust DNN Embeddings for Speaker Recognition, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2018-April (2018) 5329\u20135333. Doi: 10.1109\/ICASSP.2018.8461375.","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0235","doi-asserted-by":"crossref","unstructured":"A. Nagrani, J.S. Chung, A. Zisserman, VoxCeleb: a large-scale speaker identification dataset, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2017-August (2017) 2616\u20132620. Doi: 10.21437\/Interspeech.2017-950.","DOI":"10.21437\/Interspeech.2017-950"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0240","unstructured":"M. Freitag, S. Amiriparian, S. Pugachevskiy, N. Cummins, B. Schuller, auDeep: Unsupervised Learning of Representations from Audio with Deep Recurrent Neural Networks, Journal of Machine Learning Research 18 (2018) 1\u20135. http:\/\/jmlr.org\/papers\/v18\/17-406.html (accessed August 13, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0245","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention Is All You Need, Adv Neural Inf Process Syst 2017-December (2017) 5999\u20136009. https:\/\/arxiv.org\/abs\/1706.03762v7 (accessed August 13, 2024)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0250","series-title":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 6","first-page":"3795","article-title":"Alzheimer disease recognition using speech-based embeddings from pre-trained models","author":"Gauder","year":"2021"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0255","series-title":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 6","first-page":"3780","article-title":"Detecting cognitive decline using speech only: the ADReSSo challenge","author":"Luz","year":"2021"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0260","doi-asserted-by":"crossref","unstructured":"M. Rohanian, Q. Mary, J. Hough, M. Purver, Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer\u2019s Dementia recognition from spontaneous speech, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2020-October (2020) 2187\u20132191. Doi: 10.21437\/Interspeech.2020-2721.","DOI":"10.21437\/Interspeech.2020-2721"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2021.101298","article-title":"An automatic Alzheimer\u2019s disease classifier based on spontaneous spoken English","volume":"72","author":"Bertini","year":"2022","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0270","doi-asserted-by":"crossref","unstructured":"M.S.S. Syed, Z. Syed, M. Lech, E. Pirogova, Automated screening for Alzheimer\u2019s dementia through spontaneous speech, in: International Speech Communication Association, Baixas, France, 2020: pp. 2222\u20132226. Doi: 10.21437\/Interspeech.2020-3158.","DOI":"10.21437\/Interspeech.2020-3158"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0275","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2021.624683","article-title":"Exploring deep transfer learning techniques for Alzheimer\u2019s dementia detection","volume":"3","author":"Zhu","year":"2021","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0280","doi-asserted-by":"crossref","unstructured":"J. Koo, J.H. Lee, J. Pyo, Y. Jo, K. Lee, Exploiting Multi-Modal Features From Pre-trained Networks for Alzheimer\u2019s Dementia Recognition, (2020). http:\/\/arxiv.org\/abs\/2009.04070.","DOI":"10.21437\/Interspeech.2020-3153"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0285","doi-asserted-by":"crossref","unstructured":"R. Pappagari, J. Cho, L. Moro-Vel\u00e1zquez, N. Dehak, Using State of the Art Speaker Recognition and Natural Language Processing Technologies to Detect Alzheimer\u2019s Disease and Assess its Severity, in: Interspeech, 2020. https:\/\/api.semanticscholar.org\/CorpusID:226203271.","DOI":"10.21437\/Interspeech.2020-2587"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0290","doi-asserted-by":"crossref","unstructured":"A. Pompili, T. Rolland, A. Abad, The INESC-ID multi-modal system for the ADReSS 2020 challenge, in: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association, 2020: pp. 2202\u20132206. Doi: 10.21437\/Interspeech.2020-2833.","DOI":"10.21437\/Interspeech.2020-2833"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0295","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2021.624659","article-title":"Learning language and acoustic models for identifying alzheimer\u2019s dementia from speech","volume":"3","author":"Shah","year":"2021","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0300","first-page":"3830","article-title":"Automatic detection of Alzheimer\u2019s disease using spontaneous speech only","author":"Chen","year":"2021","journal-title":"Interspeech"},{"key":"10.1016\/j.ijmedinf.2025.106208_b0305","unstructured":"S. Figueiredo, V. Barfod, Boston Diagnostic Aphasia Examination (BDAE), (2012)."},{"key":"10.1016\/j.ijmedinf.2025.106208_b0310","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1001\/archneur.1994.00540180063015","article-title":"The natural history of Alzheimer\u2019s disease: description of study cohort and accuracy of diagnosis","volume":"51","author":"Becker","year":"1994","journal-title":"Arch. Neurol."}],"container-title":["International Journal of Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505625004253?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505625004253?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T16:17:54Z","timestamp":1786033074000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1386505625004253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":62,"alternative-id":["S1386505625004253"],"URL":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.106208","relation":{},"ISSN":["1386-5056"],"issn-type":[{"value":"1386-5056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TransformerCARE: A novel speech analysis pipeline using transformer-based models and audio augmentation techniques for cognitive impairment detection","name":"articletitle","label":"Article Title"},{"value":"International Journal of Medical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.106208","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"106208"}}