Acoustic and Language Based Deep Learning Approaches for Alzheimer's Dementia Detection From Spontaneous Speech
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Current methods for early diagnosis of Alzheimer's Dementia include structured questionnaires, structured interviews, and various cognitive tests. Language difficulties are a major problem in dementia as linguistic skills break down. Current methods do not provide robust tools to capture the true nature of language deficits in spontaneous speech. Early detection of Alzheimer's Dementia (AD) from spontaneous speech overcomes the limitations of earlier approaches as it is less time consuming, can be done at home, and is relatively inexpensive. In this work, we re-implement the existing NLP methods, which used CNN-LSTM architectures and targeted features from conversational transcripts. Our work sheds light on why the accuracy of these models drops to 72.92% on the ADReSS dataset, whereas, they gave state of the art results on the DementiaBank dataset. Further, we build upon these language input-based recurrent neural networks by devising an end-to-end deep learning-based solution that performs a binary classification of Alzheimer's Dementia from the spontaneous speech of the patients. We utilize the ADReSS dataset for all our implementations and explore the deep learning-based methods of combining acoustic features into a common vector using recurrent units. Our approach of combining acoustic features using the Speech-GRU improves the accuracy by 2% in comparison to acoustic baselines. When further enriched by targeted features, the Speech-GRU performs better than acoustic baselines by 6.25%. We propose a bi-modal approach for AD classification and discuss the merits and opportunities of our approach.
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
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing
Eyben, F., Scherer, K. R., Schuller, B. W., Sundberg, J., Andre, E., Busso, C., Devillers, L. Y., Epps, J., Laukka, P., Narayanan, S. S., et al. (2016) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2015.2457417 · Cited by 1,818 · cited 3×
“…(2) Concreteness which is a measure of word’s tangibility, (3) Familiarity which is a (Schuller et al., 2010). eGeMAPS: The eGeMAPS feature set (Eyben et al., 2015) is a result of attempts to reduce other feature sets to a basic set of 88 features with theoretical significance (Eyben et al., 2015).”
BackgroundMethodThe worldwide costs of dementia 2015 and comparisons with 2010
Wimo, A., Guerchet, M., Ali, G., Wu, Y., Prina, A. M., Winblad, B., Jönsson, L., Liu, Z., & Prince, M. (2017) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2016.07.150 · Cited by 1,066 · cited 1×
“By 2030, it is estimated that the global cost of dementia could grow to US$ 2 trillion, which could overwhelm health and social care systems (Wimo et al., 2017).”
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 3×
“…language-based methods, we observe that deep learning based approaches (Orimaye et al., 2016; Karlekar et al., 2018; Di Palo and Parde, 2019; Kong et al., 2019) outperform pre-deep learning approaches (Orimaye et al., 2014; Fraser et al., 2016) on the DementiaBank dataset (Becker et al., 1994).”
MethodThe Natural History of Alzheimer's Disease: Description of Study Cohort and Accuracy of Diagnosis
Becker, J. T. (1994) · Archives of Neurology · doi:10.1001/archneur.1994.00540180063015 · Cited by 576
Multimodal sentiment analysis with word-level fusion and reinforcement learning
Chen, M., Wang, S., Liang, P. P., Baltrušaitis, T., Zadeh, A., & Morency, L.-P. (2017) · Proceedings of the 19th ACM International Conference on Multimodal Interaction · doi:10.1145/3136755.3136801 · Cited by 334 · cited 1×
“…of the most promising solution, which has proven to be successful in the context of multimodal sentiment analysis is focusing on word-level fusion (Chen et al., 2017), where they align the words with the speech segment of each word and generate combined Gated Multimodal Embeddings (GME), rather…”
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
Orimaye, S. O., Wong, J. S.-M., & Golden, K. J. (2014) · Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w14-3210 · Cited by 116 · cited 1×
“, 2019) outperform pre-deep learning approaches (Orimaye et al., 2014; Fraser et al., 2016) on the DementiaBank dataset (Becker et al.”
Method
Cited by
Speech- and language-based classification of Alzheimer's disease: a systematic review
Vigo, I., Coelho, L., & Reis, S. (2022) · Bioengineering · doi:10.3390/bioengineering9010027 · Cited by 83
Speech based detection of Alzheimer's disease: a survey of AI techniques, datasets and challenges
Ding, K., Chetty, M., Noori Hoshyar, A., Bhattacharya, T., & Klein, B. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10961-6 · Cited by 82
Martinc, M., Haider, F., Pollak, S., & Luz, S. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.642647 · Cited by 55
“…but the analysis of continuous speech has been progressively seen by researchers as a source of information that may support diagnosis of dementia and related conditions (Lopez-de Ipiña et al., 2015, 2016; Luz et al., 2018; Toth et al., 2018; Haulcy and Glass, 2021; Mahajan and Baths, 2021).”
BackgroundFang, C., Markuzon, N., Patel, N., & Rueda, J.-D. (2022) · Value in Health · doi:10.1016/j.jval.2022.06.004 · Cited by 36
Metadata
- Authors
- Mahajan, P., & Baths, V.
- Venue
- Frontiers in Aging Neuroscience
- Publisher
- Frontiers Media SA
- Published
- 2021-02-05
- Volume
- 13
- Pages
- 623607-623607
- ISSN
- 1663-4365 (ISSN-L)
- OpenAlex
- W3129165846
- Cited by
- 89
- References
- 8
- FWCI
- 8.88
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Acoustic and Language Based Deep Learning Approaches for Alzheimer's Dementia Detection From Spontaneous Speech. https://app.cochat.ai/papers/10.3389/fnagi.2021.623607
- The paper
- Mahajan, P., & Baths, V. (2021). Acoustic and Language Based Deep Learning Approaches for Alzheimer's Dementia Detection From Spontaneous Speech. Frontiers in Aging Neuroscience. https://doi.org/10.3389/fnagi.2021.623607
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.