Exploring Language-Agnostic Speech Representations Using Domain Knowledge for Detecting Alzheimer’s Dementia
Abstract
We explore ways to use speech data to screen for indications of Alzheimer’s dementia (AD). In particular, we describe our approach to the ICASSP 2023 Signal Processing Grand Challenge, which involves extrapolating from models learned from English speech samples, to Greek speech samples, to determine which subjects have AD. By using acoustic and linguistic features, inspired by clinical research on AD, our top-performing classification model achieves 69% accuracy in distinguishing AD patients from healthy controls, and our regression model attains an RMSE of 4.8 for inferring cognitive testing scores. These outcomes underscore the potential of our explainable model for detecting cognitive decline in AD patients via speech, and its applicability in clinical settings.
Integrity signals
Registry
Cites
Statistics
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?
Support vector machine (SVM) is a commonly employed algorithm in disease diagnosis.
“The SVM [9] is another commonly employed algorithm in disease diagnosis [42,43,44].”
From A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis (2024) · cites this paper as [42]
Shah et al. achieved accuracy 0.696 and RMSE 4.8 on ADReSS-M using word-level duration, pause rate, and speech intelligibility features from speech and text.
“| Shah et al. [42] | Word-level duration feature set, pause rate data set, speech intelligibility feature set | speech, text | ADReSS-M | Accuracy: 0.696, RMSE: 4.8 |”
From A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis (2024) · cites this paper as [42]
The citation lists haven’t been fetched yet
References 5 · Cited by 19
- Authors
- Shah, Z., Qi, S.-A., Wang, F., Farrokh, M., Tasnim, M., Stroulia, E., Greiner, R., Plitsis, M., & Katsamanis, A.
- Affiliations
- University of Alberta (CA)
- Institute for Language and Speech Processing (GR)
- ORCID
- Venue
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2023-06-04
- Pages
- 1-2
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W4372260565
- Cited by
- 19
- References
- 5
- Citations by year
- 2026: 4 · 2025: 6 · 2024: 8 · 2023: 1
- FWCI
- 11.19
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Keywords
- speech analysis, cross-lingual transfer, acoustic features, linguistic features, cognitive decline screening, explainable models
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
