{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:20:06Z","timestamp":1792790406951,"version":"4.5.0"},"posted":{"date-parts":[[2026,9,25]]},"group-title":"Neurology","reference-count":54,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"funder":[{"name":"National Institute on Aging","award":["AG051633"],"award-info":[{"award-number":["AG051633"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Institute on Aging","award":["AG057470-01"],"award-info":[{"award-number":["AG057470-01"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Institute on Aging","award":["AG042127"],"award-info":[{"award-number":["AG042127"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Institute on Aging","award":["AG062786"],"award-info":[{"award-number":["AG062786"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Institute on Aging","award":["K24AG062786"],"award-info":[{"award-number":["K24AG062786"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>INTRODUCTION<\/jats:title>\n                  <jats:p>Voice data combined with large language models may detect cognitive impairment, yet an interpretable framework has not been formally established. We developed and validated a scalable and interpretable framework, the Neurocognitive Speech Taxonomy (NST).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>METHODS<\/jats:title>\n                  <jats:p>NST maps 314 voice features to 7 neurocognitive domains derived from neuropsychology, speech pathology, neurology and related fields. The domains capture features including articulatory precision, cognitive-linguistic, executive fluency &amp; planning, phonation &amp; laryngeal control, prosodic modulation, lexical-semantic, and morphosyntactic complexity. We evaluated NST structural stability, clinical validity and racial-educational equity in three cohorts (total N = 1,479). Cohort data included demographic and neuropsychological evaluations and AD biomarker status. We tested whether NST scores distinguish cognitive status (unimpaired vs impaired) and AD-biomarker status, track cognitive change, and correlate with AD neuroimaging measures.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>RESULTS<\/jats:title>\n                  <jats:p>\n                    NST showed stable cross-cohort structure (Mantel\n                    <jats:italic>r<\/jats:italic>\n                    = 0.71-0.77) and differentiated MCI (\n                    <jats:italic>d<\/jats:italic>\n                    = \u22120.39) and AD biomarker status (\n                    <jats:italic>d<\/jats:italic>\n                    = \u22120.23). NST tracked longitudinal cognitive change, correlated with hippocampal volume (r up to 0.28, P &lt; .001), and showed smaller racial and educational disparities relative to standard cognitive testing (NST d = 0.03-0.33, MoCA d = 0.37-0.72).\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>DISCUSSION<\/jats:title>\n                  <jats:p>NST provides a validated neurocognitive construct that facilitates interpretation of AI-driven voice biomarkers of AD. This study was not registered in a public trials registry.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.09.23.26363671","type":"posted-content","created":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:20:15Z","timestamp":1790382015000},"source":"Crossref","is-referenced-by-count":0,"title":["A neurocognitive speech taxonomy for voice biomarkers of Alzheimer\u2019s disease"],"prefix":"10.64898","author":[{"given":"Brandon","family":"Henley","sequence":"first","affiliation":[{"name":"Department of Neurology, Baylor College of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Baylor College of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Sober","sequence":"additional","affiliation":[{"name":"Department of Neurology, Baylor College of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vince","family":"Calhoun","sequence":"additional","affiliation":[{"name":"Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felicia","family":"Goldstein","sequence":"additional","affiliation":[{"name":"Department of Neurology, Emory University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ihab","family":"Hajjar","sequence":"additional","affiliation":[{"name":"Department of Neurology, Baylor College of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026092903150573000_2026.09.23.26363671v1.1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.71345"},{"key":"2026092903150573000_2026.09.23.26363671v1.2","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afaf316"},{"key":"2026092903150573000_2026.09.23.26363671v1.3","doi-asserted-by":"publisher","DOI":"10.1017\/s1355617702813157"},{"key":"2026092903150573000_2026.09.23.26363671v1.4","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e318230208a"},{"key":"2026092903150573000_2026.09.23.26363671v1.5","doi-asserted-by":"publisher","DOI":"10.1177\/0891988714524630"},{"key":"2026092903150573000_2026.09.23.26363671v1.6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1220"},{"key":"2026092903150573000_2026.09.23.26363671v1.7","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume":"202","year":"2023","journal-title":"Proceedings of the 40th International Conference on Machine Learning."},{"key":"2026092903150573000_2026.09.23.26363671v1.8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"issue":"1","key":"2026092903150573000_2026.09.23.26363671v1.9","first-page":"112","article-title":"Automatic speech analysis for the assessment of patients with predementia and Alzheimer\u2019s disease","volume":"1","year":"2015","journal-title":"Alzheimers Dement Diagn Assess Dis Monit"},{"key":"2026092903150573000_2026.09.23.26363671v1.10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0236009"},{"key":"2026092903150573000_2026.09.23.26363671v1.11","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1996.03530310034029"},{"key":"2026092903150573000_2026.09.23.26363671v1.12","doi-asserted-by":"publisher","DOI":"10.1037\/0882-7974.16.2.227"},{"key":"2026092903150573000_2026.09.23.26363671v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2004.06.019"},{"key":"2026092903150573000_2026.09.23.26363671v1.14","doi-asserted-by":"publisher","DOI":"10.1007\/s44163-023-00049-5"},{"key":"2026092903150573000_2026.09.23.26363671v1.15","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2022.886615"},{"key":"2026092903150573000_2026.09.23.26363671v1.16","doi-asserted-by":"publisher","DOI":"10.1002\/alz.14218"},{"key":"2026092903150573000_2026.09.23.26363671v1.17","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-025-01689-8"},{"key":"2026092903150573000_2026.09.23.26363671v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2015.05.017"},{"key":"2026092903150573000_2026.09.23.26363671v1.19","doi-asserted-by":"publisher","DOI":"10.3390\/cells13131164"},{"key":"2026092903150573000_2026.09.23.26363671v1.20","doi-asserted-by":"publisher","DOI":"10.1159\/000551440"},{"key":"2026092903150573000_2026.09.23.26363671v1.21","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.35068"},{"key":"2026092903150573000_2026.09.23.26363671v1.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2004.02.058"},{"key":"2026092903150573000_2026.09.23.26363671v1.23","doi-asserted-by":"publisher","DOI":"10.1002\/dad2.12393"},{"key":"2026092903150573000_2026.09.23.26363671v1.24","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"2026092903150573000_2026.09.23.26363671v1.25","unstructured":"Boersma P , Weenink D . Praat: doing phonetics by computer. https:\/\/www.praat.org"},{"key":"2026092903150573000_2026.09.23.26363671v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"2026092903150573000_2026.09.23.26363671v1.27","doi-asserted-by":"publisher","DOI":"10.1787\/9789264043466-en"},{"key":"2026092903150573000_2026.09.23.26363671v1.28","doi-asserted-by":"publisher","DOI":"10.1002\/sim.10326"},{"key":"2026092903150573000_2026.09.23.26363671v1.29","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.1203"},{"key":"2026092903150573000_2026.09.23.26363671v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/ng2088"},{"key":"2026092903150573000_2026.09.23.26363671v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.trci.2017.10.004"},{"key":"2026092903150573000_2026.09.23.26363671v1.32","doi-asserted-by":"publisher","DOI":"10.1017\/S1355617798001374"},{"key":"2026092903150573000_2026.09.23.26363671v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2004.02.001"},{"key":"2026092903150573000_2026.09.23.26363671v1.34","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.neuropsychologia.2019.05.006","article-title":"High amyloid burden is associated with fewer specific words during spontaneous speech in individuals with subjective cognitive decline","volume":"131","year":"2019","journal-title":"Neuropsychologia"},{"key":"2026092903150573000_2026.09.23.26363671v1.35","doi-asserted-by":"publisher","DOI":"10.1002\/dad2.12203"},{"key":"2026092903150573000_2026.09.23.26363671v1.36","doi-asserted-by":"publisher","DOI":"10.1016\/0028-3932(94)00127-B"},{"key":"2026092903150573000_2026.09.23.26363671v1.37","doi-asserted-by":"publisher","DOI":"10.1007\/s10072-005-0467-9"},{"key":"2026092903150573000_2026.09.23.26363671v1.38","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awt269"},{"key":"2026092903150573000_2026.09.23.26363671v1.39","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-210134"},{"key":"2026092903150573000_2026.09.23.26363671v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/0093-934X(82)90006-2"},{"key":"2026092903150573000_2026.09.23.26363671v1.41","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.00269"},{"key":"2026092903150573000_2026.09.23.26363671v1.42","doi-asserted-by":"publisher","DOI":"10.1177\/13872877241300149"},{"key":"2026092903150573000_2026.09.23.26363671v1.43","doi-asserted-by":"publisher","DOI":"10.37349\/emed.2020.00028"},{"key":"2026092903150573000_2026.09.23.26363671v1.44","doi-asserted-by":"publisher","DOI":"10.1017\/S1355617719000560"},{"key":"2026092903150573000_2026.09.23.26363671v1.45","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.42203"},{"key":"2026092903150573000_2026.09.23.26363671v1.46","unstructured":"Gulzar K , Riedhammer K , Noth E , Maier AK , Perez-Toro PA. Bias and fairness in self- supervised acoustic representations for cognitive impairment detection. arXiv. Preprint posted online March 3, 2026. https:\/\/arxiv.org\/abs\/2603.02937"},{"key":"2026092903150573000_2026.09.23.26363671v1.47","unstructured":"Haghbin Y , Rashidi S , Zolnour A , Zolnoori M. The Voice of Equity: A Systematic Evaluation of Bias Mitigation Techniques for Speech-Based Cognitive Impairment Detection Across Architectures and Demographics. arXiv. Preprint posted online January 7, 2026. https:\/\/arxiv.org\/abs\/2601.16989"},{"key":"2026092903150573000_2026.09.23.26363671v1.48","doi-asserted-by":"publisher","DOI":"10.1093\/braincomms\/fcac231"},{"key":"2026092903150573000_2026.09.23.26363671v1.49","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-025-01877-6"},{"key":"2026092903150573000_2026.09.23.26363671v1.50","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2024.1451326"},{"key":"2026092903150573000_2026.09.23.26363671v1.51","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-024-01543-3"},{"key":"2026092903150573000_2026.09.23.26363671v1.52","doi-asserted-by":"publisher","DOI":"10.2196\/55126"},{"issue":"4","key":"2026092903150573000_2026.09.23.26363671v1.53","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.3233\/JAD-200888","article-title":"Artificial intelligence, speech, and language processing approaches to monitoring Alzheimer\u2019s disease: a systematic review","volume":"78","year":"2020","journal-title":"J Alzheimers Dis"},{"key":"2026092903150573000_2026.09.23.26363671v1.54","doi-asserted-by":"publisher","DOI":"10.1002\/alz.14530"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.23.26363671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T10:15:17Z","timestamp":1790676917000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.09.23.26363671"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":54,"URL":"https:\/\/doi.org\/10.64898\/2026.09.23.26363671","relation":{},"subject":[],"published":{"date-parts":[[2026,9,25]]},"subtype":"preprint"}}