Pauses for Detection of Alzheimer’s Disease
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Pauses, disfluencies and language problems in Alzheimer’s disease can be naturally modeled by fine-tuning Transformer-based pre-trained language models such as BERT and ERNIE. Using this method with pause-encoded transcripts, we achieved 89.6% accuracy on the test set of the ADReSS (A lzheimer’s D ementia Re cognition through S pontaneous S peech) Challenge. The best accuracy was obtained with ERNIE, plus an encoding of pauses. Robustness is a challenge for large models and small training sets. Ensemble over many runs of BERT/ERNIE fine-tuning reduced variance and improved accuracy. We found that um was used much less frequently in Alzheimer’s speech, compared to uh. We discussed this interesting finding from linguistic and cognitive perspectives.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Using uh and um in spontaneous speaking
Clark, H. (2002) · Cognition · doi:10.1016/s0010-0277(02)00017-3 · Cited by 1,235 · cited 1×
“There is a debate in the literature as to whether uh and um are intentionally produced by speakers (Clark and Fox Tree, 2002; Corley and Stewart, 2008).”
BackgroundLinguistic Features Identify Alzheimer’s Disease in Narrative Speech
Fraser, K. C., Meltzer, J. A., & Rudzicz, F. (2015) · Journal of Alzheimer's Disease · doi:10.3233/jad-150520 · Cited by 797 · cited 1×
“Fraser et al. (2016) used 370 acoustic and linguistic features to train logistic regression models for classifying AD and normal speech.”
MethodInnovative diagnostic tools for early detection of Alzheimer's disease
Laske, C., Sohrabi, H. R., Frost, S. M., López-de-Ipiña, K., Garrard, P., Buscema, M., Dauwels, J., Soekadar, S. R., Mueller, S., Linnemann, C., et al. (2015) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2014.06.004 · Cited by 316
Effects of length and syntactic complexity on initiation times for prepared utterances
Ferreira, F. (1991) · Journal of Memory and Language · doi:10.1016/0749-596x(91)90004-4 · Cited by 288 · cited 1×
“For example, if a sentence has a syntactically complex subject and a syntactically complex object, speakers tend to pause at the subject-verb phrase boundary, and pause duration increases with upcoming complexity (Ferreira, 1991).”
BackgroundAlzheimer’s Dementia Recognition Through Spontaneous Speech: The ADReSS Challenge
Luz, S., Haider, F., Fuente, S. D. L., Fromm, D., & MacWhinney, B. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2571 · Cited by 274
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 · cited 1×
“Gosztolya et al. (2019) found that acoustic and linguistic features were about equally effective for AD classi fi cation, but the combination of the two performed better than either by itself.”
BackgroundAlzheimer's disease and automatic speech analysis: A review
Pulido, M. L. B., Hernández, J. B. A., Ballester, M. Á. F., González, C. M. T., Mekyska, J., & Smékal, Z. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113213 · Cited by 120 · cited 1×
“3 Automatic Detection of AD There is a considerable literature on AD detection from continuous speech (Filiou et al., 2019; Pulido et al., 2020).”
BackgroundIrvine, C. A., Eigsti, I.-M., & Fein, D. A. (2016) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-015-2651-y · Cited by 70
Variation and Change in the Use of Hesitation Markers in Germanic Languages
Wieling, M., Grieve, J., Bouma, G., Fruehwald, J., Coleman, J., & Liberman, M. (2016) · Language Dynamics and Change · doi:10.1163/22105832-00602001 · Cited by 63 · cited 1×
“From sociolinguistic point of view, women and younger people tend to use more um vs. uh than men and older people (Tottie, 2011; Wieling et al., 2016).”
Background
Cited by
Predicting dementia from spontaneous speech using large language models
Agbavor, F., & Liang, H. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000168 · Cited by 147
“Recent work has shown encouraging results with fine-tuned BERT for AD detection [20,41].”
ResultFristed, E., Skirrow, C., Meszaros, M., Lenain, R., Meepegama, U., Papp, K. V., Ropacki, M., & Weston, J. (2022) · Brain Communications · doi:10.1093/braincomms/fcac231 · Cited by 29
“…pre-trained Transformer models to make predictions on downstream tasks: attaching a prediction head to a later layer of the Transformer and fine-tuning the entire network, 21 or using the output at a later layer as a fixed feature extractor and using these features as input to a separate model.”
Evaluating ASR for aphasia: a framework for clinically relevant transcription performance
Dupuis Desroches, J., Ménard, P. A., & Ratté, S. (2026) · Aphasiology · doi:10.1080/02687038.2026.2621235 · Cited by 1
Metadata
- Authors
- Yuan, J., Cai, X., Bian, Y., Ye, Z., & Church, K.
- Venue
- Frontiers in Computer Science
- Publisher
- Frontiers Media SA
- Published
- 2021-01-29
- Volume
- 2
- ISSN
- 2624-9898 (ISSN-L)
- OpenAlex
- W3128293209
- Cited by
- 49
- References
- 10
- FWCI
- 3.97
- Type
- journal article
- Language
- en
- Open access
- gold
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
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.