Speech-based automatic and robust detection of very early dementia
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
We provide evidence to the potential use of simple spoken tasks for automatic assessment of very early dementia. Timely detection of dementia is required for effective psychological treatment and to enable patients to participate in new drug therapy research. The technology enables automatic, cheap, remote and wide-scale screening of dementia, typically a costly and complex procedure. It can aid clinicians in the diagnosis of very early dementia, as well as assessing the disease progression. We describe the spoken tasks, and their respective languageindependent vocal feature extraction, followed by classification accuracy evaluation. We use recordings from over 60 persons, diagnosed as healthy-control (CTRL) / mildcognitive-impairment (MCI) / early-stage-Alzheimer-disease and early-mixed-dementia (AD). We present a new data regularization technique to overcome data sparseness due to the limited data set size. Next, we present a comprehensive statistical analysis, showing that the suggested classifier generalizes, and revealing the role and the statistical importance of the different spoken tasks and their respective vocal features. We demonstrate classification accuracy of about 80% for CTRL vs. MCI and MCI vs. AD, and 87% for CTRL vs. AD, all shown to generalize. This provides an evidence for potential use for automatic detection of very early dementia.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Voice interfaces have been investigated as a potential way to detect cognitive decline and early signs of dementia from linguistic and speech patterns [37], [116], [117].”
From Conversational Affective Social Robots for Ageing and Dementia Support (2022) · cites this paper as [117]
Citations
Cites
Connected speech as a marker of disease progression in autopsy-proven Alzheimer’s disease
Ahmed, S., Haigh, A.-M. F., de Jager, C. A., & Garrard, P. (2013) · Brain · doi:10.1093/brain/awt269 · Cited by 362 · cited 2×
“The studies [3], [4], [5], [7], [8], [9] reported correlation between dementia and certain vocal features.”
BackgroundResultA Critical Assessment of Feature Selection Methods for Biomarker Discovery in Clinical Proteomics
Christin, C., Hoefsloot, H. C. J., Smilde, A. K., Hoekman, B., Suits, F., Bischoff, R., & Horvatovich, P. L. (2012) · Molecular & Cellular Proteomics · doi:10.1074/mcp.m112.022566 · Cited by 165 · cited 3×
“The feature selection techniques known as wrapper or embedded methods [14], were found to perform poorly in terms of classification accuracy, in our case.”
BackgroundMethodCognition, language, and clinical pathological features of non-Alzheimer's dementias: An overview
Reilly, J., Rodriguez, A. D., Lamy, M., & Neils-Strunjas, J. (2010) · Journal of Communication Disorders · doi:10.1016/j.jcomdis.2010.04.011 · Cited by 119 · cited 1×
“Various types of dementia affect human speech and language; deficits in those domains have proven to be strong predictors for the disease progression [3], [6].”
BackgroundThomas, C., Keselj, V., Cercone, N., Rockwood, K., & Asp, E. (2006) · IEEE International Conference Mechatronics and Automation, 2005 · doi:10.1109/icma.2005.1626789 · Cited by 110 · cited 1×
“Useful verbal metrics, which require automatic speech recognition for their evaluation, include speech richness based on the vocabulary size, and proportions of different parts of speech such as verbs and nouns [10].”
BackgroundEvaluation of speech-based protocol for detection of early-stage dementia
Satt, A., Sorin, A. S., Ronen, O., Barkan, O., Kompatsiaris, I. Y., Kokonozi, A., & Tsolaki, M. (2013) · Interspeech (USB) · doi:10.21437/interspeech.2013-32 · Cited by 78 · cited 2×
“It significantly extends the work in [11], and provides clear evidence for the effectiveness of speech processing technologies in supporting dementia assessment.”
BackgroundMethodSelf-citationAcoustic Markers Associated with Impairment in Language Processing in Alzheimer's Disease
Meilán, J. J. G., Martínez-Sánchez, F., Carro, J., Sánchez, J. A., & Pérez, E. (2012) · The Spanish journal of psychology · doi:10.5209/rev_sjop.2012.v15.n2.38859 · Cited by 64 · cited 2×
“The studies [3], [4], [5], [7], [8], [9] reported correlation between dementia and certain vocal features.”
BackgroundResultRecommendations for ICT use in Alzheimer's disease assessment: Monaco CTAD expert meeting
Robert, P. H., Konig, A., Andrieu, S., Bremond, F., Chemin, I., Chung, P. C., Dartigues, J. F., Dubois, B., Feutren, G., Guillemaud, R., et al. (2013) · The Journal of nutrition, health and aging · doi:10.1007/s12603-013-0046-3 · Cited by 46 · cited 1×
“Early detection of dementia and MCI is necessary to optimize the patient’s care and the support to caregivers, and to provide better tools for clinical research [1].”
BackgroundSelf-citationHallikainen, I., Hänninen, T., Fraunberg, M., Hongisto, K., Välimäki, T., Hiltunen, A., Karppi, P., Sivenius, J., Soininen, H., & Koivisto, A. M. (2013) · International Psychogeriatrics · doi:10.1017/s1041610213000653 · Cited by 36 · cited 1×
“Research shows that psychological treatment to AD patients, which begins at the very early stage of the disease, alleviates psychological and behavioral symptoms [2].”
Backgroundde Ipiña, K. L., Alonso, J. B., Barroso, N., Faúndez-Zanuy, M., Ecay‐Torres, M., Solé‐Casals, J., Travieso, C. M., Estanga, A., & Ezeiza, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35395-6_55 · Cited by 34 · cited 2×
“The studies [3], [4], [5], [7], [8], [9] reported correlation between dementia and certain vocal features.”
BackgroundResultSocial correlates of turn-taking behavior
Grothendieck, J., Gorin, A. L., & Borges, N. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4960691 · Cited by 21
Cited by
Toth, L., Hoffmann, I., Gosztolya, G., Vincze, V., Szatloczki, G., Banreti, Z., Pakaski, M., & Kalman, J. (2018) · Current Alzheimer Research · doi:10.2174/1567205014666171121114930 · Cited by 290
“With these, one can separate voiced and voiceless segments, speech and non-speech, or periodic-aperiodic parts [9, 30].”
InfluentialSzatloczki, G., Hoffmann, I., Vincze, V., Kalman, J., & Pakaski, M. (2015) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2015.00195 · Cited by 249
“In the MCI phase, the most characteristic linguistic changes are longer hesitations and a lower speech rate in spontaneous speech (Hoffmann et al., 2010; Roark et al., 2011; Jarrold et al., 2014; Satt et al., 2014).”
BackgroundMethodA Transdiagnostic Review of Negative Symptom Phenomenology and Etiology
Strauss, G. P., & Cohen, A. S. (2017) · Schizophrenia Bulletin · doi:10.1093/schbul/sbx066 · Cited by 216
Gosztolya, G., Vincze, V., Tóth, L., Pákáski, M., Kálmán, J., & Hoffmann, I. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2018.07.007 · Cited by 196
Haider, F., de la Fuente, S., & Luz, S. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2955022 · Cited by 190
“ing results on a French dataset later on [49].”
Background
Metadata
- Authors
- Satt, A., Hoory, R., König, A., Aalten, P., & Robert, P. H.
- Venue
- Interspeech 2014
- Publisher
- ISCA
- Published
- 2014-09-14
- Pages
- 2538-2542
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2401240531
- Cited by
- 76
- References
- 11
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 3 · 2023: 10 · 2022: 6 · 2021: 11 · 2020: 10 · 2019: 8 · 2018: 7 · 2017: 5 · 2016: 5 · 2015: 3
- FWCI
- 17.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Keywords
- Alzheimer's disease, mild cognitive impairment, mixed dementia, language-independent features, automatic classification, data regularization, data sparsity, remote screening, disease progression assessment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Speech-based automatic and robust detection of very early dementia. https://app.cochat.ai/papers/10.21437/interspeech.2014-544
- The paper
- Satt, A., Hoory, R., König, A., Aalten, P., & Robert, P. H. (2014). Speech-based automatic and robust detection of very early dementia. Interspeech 2014. https://doi.org/10.21437/interspeech.2014-544
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.