Temporal integration of text transcripts and acoustic features for Alzheimer’s diagnosis based on spontaneous speech
Open accessAbstract
Background:Advances in machine learning (ML) technology have opened new avenues for detection and monitoring of cognitive decline. In this study, a multimodal approach to Alzheimer's dementia detection based on the patient's spontaneous speech is presented. This approach was tested on a standard, publicly available Alzheimer's speech dataset for comparability. The data comprise voice samples from 156 participants (1:1 ratio of Alzheimer's to control), matched by age and gender. Materials and Methods:A recently developed Active Data Representation (ADR) technique for voice processing was employed as a framework for fusion of acoustic and textual features at sentence and word level. Temporal aspects of textual features were investigated in conjunction with acoustic features in order to shed light on the temporal interplay between paralinguistic (acoustic) and linguistic (textual) aspects of Alzheimer's speech. Combinations between several configurations of ADR features and more traditional bag-of-n-grams approaches were used in an ensemble of classifiers built and evaluated on a standardised dataset containing recorded speech of scene descriptions and textual transcripts. Results:Employing only semantic bag-of-n-grams features, an accuracy of 89.58% was achieved in distinguishing between Alzheimer's patients and healthy controls. Adding temporal and structural information by combining bag-of-n-grams features with ADR audio/textual features, the accuracy could be improved to 91.67% on the test set. An accuracy of 93.75% was achieved through late fusion of the three best feature configurations, which corresponds to a 4.7% improvement over the best result reported in the literature for this dataset. Conclusion:The proposed combination of ADR audio and textual features is capable of successfully modelling temporal aspects of the data. The machine learning approach toward dementia detection achieves best performance when ADR features are combined with strong semantic bag-of-n-grams features. This combination leads to state-of-the-art performance on the AD classification task.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 [43]
Martinc et al. achieved accuracy 0.9167 on Dementia-Bank Pit using bag-of-n-grams text features and eGeMAPS voice features.
“| Martinc et al. [43] | bag-of-n-grams features (text) eGeMAPS feature set (voice) | speech, text | Dementia- Bank Pit | Accuracy: 0.9167 |”
From A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis (2024) · cites this paper as [43]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 3× · see citing works
“…approach as in our classification experiments described in detail in section 5.1, that is, we trained and tested 50 random forest classifiers (Breiman, 2001) with 50 trees of maximum depth 5 by employing leave-one-out cross validation (LOOCV) on the training set, each time using a different…”
BackgroundMethodInfluentialVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1× · see citing works
“BERT’s attention mechanism consists of 12 attention heads (Vaswani et al., 2017)—square matrices linking pairs of tokens within a given text.”
BackgroundXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 2× · see citing works
“…classifiers and k ∈ 10, 20, ..., 80 values, in which we employed 5 classifiers from the Scikit library (Pedregosa et al., 2011), namely Xgboost (Chen and Guestrin, 2016) (with 50 gradient boosted trees with max depth of 10), random forest (with 50 trees of max depth of 5), SVM (with linear…”
MethodBERT: 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 48,293 · cited 4× · see citing works
“1 and obtain a strong baseline, we also leverage the BERT model (Devlin et al., 2019).”
MethodInfluentialGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2× · see citing works
“By combining such features with timing and pause information, and GloVe word vectors (Pennington et al., 2014) they were able to achieve 80% F 1 score on manually transcribed data, and F 1 = 72% on ASR outputs.”
MethodAdvances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,881 · see citing works
Baeza-Yates, R. A., & Ribeiro-Neto, B. A. (1999) · Cited by 11,498 · see citing works
Kohonen, T. (1990) · Proceedings of the IEEE · doi:10.1109/5.58325 · Cited by 8,414 · see citing works
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 2× · see citing works
“The eGeMAPS feature set corresponds to a basic set of acoustic features based on their potential to detect physiological changes in voice production, as well as theoretical significance and proven usefulness in previous studies (Eyben et al., 2016).”
BackgroundMethodStanza: A Python Natural Language Processing Toolkit for Many Human Languages
Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.18653/v1/2020.acl-demos.14 · Cited by 1,505 · see citing works
ERNIE: Enhanced Language Representation with Informative Entities
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., & Liu, Q. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1139 · Cited by 1,482 · cited 5× · see citing works
“The modified transcripts with encoded pauses were fed into an ensemble of 50 BERT (Devlin et al., 2019) and 50 ERNIE (Zhang et al., 2019) models, and majority voting was employed to derive the final predictions on the test set.”
MethodResultInfluentialLinguistic 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× · see citing works
“Therefore, this dataset has been used in several studies, including the studies by Fraser et al. (2016), Hernández-Domínguez et al. (2018), and others (Yancheva and Rudzicz, 2016; Luz, 2017; Orimaye et al., 2017; Guo et al., 2019; Mirheidari et al., 2019b; Haider et al., 2020).”
MethodHodges, J. R. (1995) · Neuropsychologia · doi:10.1016/0028-3932(94)00127-b · Cited by 644 · cited 1× · see citing works
“This heterogeneity seems to be more evident in AD than in specific disorders such as primary progressive aphasia (Ahmed et al., 2013), especially in early stages of AD (Hodges and Patterson, 1995).”
Speaker identification on the SCOTUS corpus
Yuan, J., & Liberman, M. (2008) · The Journal of the Acoustical Society of America · doi:10.1121/1.2935783 · Cited by 600 · cited 1× · see citing works
“Next, the processed transcripts were force-aligned with the speech recordings using the Penn Phonetics Lab Forced Aligner (Yuan and Liberman, 2008), which labels the pauses between words with ‘sp’ and produces time stamps for each word and for each pause.”
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 · see citing works
Automatic speech analysis for the assessment of patients with predementia and Alzheimer's disease
König, A., Satt, A., Sorin, A., Hoory, R., Toledo‐Ronen, O., Derreumaux, A., Manera, V., Verhey, F., Aalten, P., Robert, P. H., et al. (2015) · Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring · doi:10.1016/j.dadm.2014.11.012 · Cited by 380 · cited 1× · see citing works
“Similar machine learning methods were used by König et al. (2015), who reported an accuracy of 79% when distinguishing MCI participants from healthy controls; 94% for AD vs. healthy; and 80% for MCI vs. AD.”
MethodConnected 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 1× · see citing works
“This heterogeneity seems to be more evident in AD than in specific disorders such as primary progressive aphasia (Ahmed et al., 2013), especially in early stages of AD (Hodges and Patterson, 1995).”
BackgroundSpoken Language Derived Measures for Detecting Mild Cognitive Impairment
Roark, B., Mitchell, M., Hosom, J.-P., Hollingshead, K., & Kaye, J. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2112351 · Cited by 355 · cited 1× · see citing works
“A study by Roark et al. (2011) used natural language processing (NLP) and automatic speech recognition (ASR) to automatically annotate and time-align a few spoken language features (pause frequency and duration), and compared these methods to manual analysis.”
MethodopenSMILE - The Munich Versatile and Fast Open-Source Audio Feature Extractor
Eyben, F. ;. (2013) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 322 · see citing works
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 · cited 3× · see citing works
“Toth et al. (2018), for instance, found that filled pauses (sounds like “hmmm,” etc.) could not be reliably detected by human annotators, and that detection improved by using ASR-generated transcriptions.”
InfluentialAlzheimer’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 · see citing works
Self-citationGarcía, S. D. L. F., Ritchie, C. W., & Luz, S. F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.06047 · Cited by 265 · see citing works
Self-citationHaider, F., García, S. D. L. F., & Luz, S. F. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2955022 · Cited by 191 · see citing works
Self-citationAge Correction in Dementia – Matching to a Healthy Brain
Dukart, J., Schroeter, M. L., Mueller, K., & Initiative, T. A. D. N. (2011) · PLoS ONE · doi:10.1371/journal.pone.0022193 · Cited by 183 · cited 1× · see citing works
“As age and gender are considered major risk factors for dementia (Dukart et al., 2011), these variables are possible confounders between the AD and non-AD groups.”
BackgroundAided diagnosis of dementia type through computer-based analysis of spontaneous speech
Jarrold, W., Peintner, B., Wilkins, D., Vergryi, D., Richey, C., Gorno-Tempini, M. L., & Ogar, J. (2014) · Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality · doi:10.3115/v1/w14-3204 · Cited by 178 · cited 1× · see citing works
“Jarrold et al. (2014) worked with a dataset consisting of semi-structured interviews from 9 healthy participants, 9 with AD, 9 with frontotemporal dementia, 13 with semantic dementia, and 8 with progressive nonfluent aphasia.”
MethodA systematic literature review of automatic Alzheimer’s disease detection from speech and language
Petti, U., Baker, S., & Korhonen, A. (2020) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa174 · Cited by 168 · cited 1× · see citing works
“…machine learning (ML) technology has opened new avenues for more comprehensive monitoring of cognitive function, and tests based on spontaneous speech and language data have emerged as possible tools for diagnostic and prognostic assessment (de la Fuente Garcia et al., 2020; Petti et al., 2020).”
8th Annual Conference of the International Speech Communication Association
Murray, G., & Renals, S. J. (2007) · Cited by 166 · see citing works
Predicting probable Alzheimer's disease using linguistic deficits and biomarkers
Orimaye, S. O., Wong, J. S.-M., Golden, K. J., Wong, C. P., & Soyiri, I. N. (2017) · BMC Bioinformatics · doi:10.1186/s12859-016-1456-0 · Cited by 158 · cited 1× · see citing works
“Therefore, this dataset has been used in several studies, including the studies by Fraser et al. (2016), Hernández-Domínguez et al. (2018), and others (Yancheva and Rudzicz, 2016; Luz, 2017; Orimaye et al., 2017; Guo et al., 2019; Mirheidari et al., 2019b; Haider et al., 2020).”
MethodBalagopalan, A., Eyre, B., Rudzicz, F., & Novikova, J. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2557 · Cited by 144 · see citing works
López-de-Ipiña, K., Alonso, J. B., Solé-Casals, J., Barroso, N., Henriquez, P., Faundez-Zanuy, M., Travieso, C. M., Ecay-Torres, M., Martínez-Lage, P., & Eguiraun, H. (2015) · Cognitive Computation · doi:10.1007/s12559-013-9229-9 · Cited by 132 · cited 1× · see citing works
“…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).”
BackgroundDetecting Dementia Through Interactive Computer Avatars
Tanaka, H., Adachi, H., Ukita, N., Ikeda, M., Kazui, H., Kudo, T., & Nakamura, S. (2017) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2017.2752152 · Cited by 127 · cited 1× · see citing works
“Tanaka et al. (2017) collected dialogue, eye-tracking and video data from 29 Japanese participants who conducted structured dialogues with a virtual agent.”
BackgroundCognition, language, and clinical pathological features of non-Alzheimer's dementias: An overview
Reilly, J. J., Rodriguez, A. D., Lamy, M., & Neils‐Strunjas, J. (2010) · Journal of Communication Disorders · doi:10.1016/j.jcomdis.2010.04.011 · Cited by 120 · cited 1× · see citing works
“Language research into AD has employed high-level features such as information content, comprehension of complexity, picture naming and word-list generation as predictors of disease progression (Reilly et al., 2010).”
BackgroundDisfluencies and Fine-Tuning Pre-Trained Language Models for Detection of Alzheimer’s Disease
Yuan, J., Bian, Y., Cai, X., Huang, J., Ye, Z., & Church, K. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2516 · Cited by 116 · cited 1× · see citing works
“The winning team (Yuan et al., 2020) leveraged audio recordings to obtain information about pauses in speech, encoding them as punctuation.”
BackgroundHernández-Domínguez, L., Ratté, S., Sierra, G., & Roche-Bergua, A. (2018) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1016/j.dadm.2018.02.004 · Cited by 113 · see citing works
Describing the Cookie Theft picture
Cummings, L. (2019) · Pragmatics and Society · doi:10.1075/ps.17011.cum · Cited by 112 · cited 3× · see citing works
“As Cummings (2019) observed, while the Cookie Theft picture is a static scene, causal and temporal relations can be inferred from the various elements depicted in it.”
BackgroundFinding a balance: The Carolinas Conversation Collection
Pope, C. A., & Davis, B. H. (2011) · Corpus Linguistics and Linguistic Theory · doi:10.1515/cllt.2011.007 · Cited by 108 · cited 1× · see citing works
“A more recent study by Luz et al. (2018) extracted graph-based features encoding turn-taking patterns and speech rate (Luz, 2009) from the Carolina Conversations Collection (Pope and Davis, 2011) of spontaneous interviews of AD patients and healthy controls.”
BackgroundClassifying Alzheimer's Disease Using Audio and Text-Based Representations of Speech
Haulcy, R., & Glass, J. R. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.624137 · Cited by 105 · cited 1× · see citing works
“…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).”
BackgroundPotential New Approaches for Diagnosis of Alzheimer's Disease and Related Dementias
Turner, R. S., Stubbs, T., Davies, D. A., & Albensi, B. C. (2020) · Frontiers in Neurology · doi:10.3389/fneur.2020.00496 · Cited by 95 · cited 1× · see citing works
“The complex multimodal ways in which AD symptoms may appear calls for increasingly interdisciplinary research (Turner et al., 2020).”
BackgroundMahajan, P., & Baths, V. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.623607 · Cited by 89 · cited 2× · see citing works
“…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).”
BackgroundRohanian, M., Hough, J., & Purver, M. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2721 · Cited by 84 · see citing works
Dementia detection using automatic analysis of conversations
Mirheidari, B., Blackburn, D., Walker, T., Reuber, M., & Christensen, H. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2018.07.006 · Cited by 82 · cited 1× · see citing works
“Mirheidari et al. (2019a) compared the accuracy of automated conversational analysis (ML with a combination of acoustic and linguistic features) for detection of AD on recorded doctor-patient consultations and on dialogues recorded through human-robot interaction.”
BackgroundSpeech-Based Detection of Alzheimer’s Disease in Conversational German
Weiner, J., Herff, C., & Schultz, T. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-100 · Cited by 77 · cited 1× · see citing works
“Weiner et al. (2016) analysed semi-structured German dialogues employing linear discriminant analysis to classify participants as healthy controls, Alzheimer’s or age-associated cognitive decline, obtaining a mean accuracy score of 85.7%.”
BackgroundInfluentialAutomated Screening for Alzheimer’s Dementia Through Spontaneous Speech
Syed, M. S. S., Syed, Z. S., Lech, M., & Pirogova, E. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-3158 · Cited by 74 · see citing works
Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity
Sarawgi, U., Zulfikar, W. D., Soliman, N., & Maes, P. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-3137 · Cited by 72 · see citing works
Exploiting Multi-Modal Features from Pre-Trained Networks for Alzheimer’s Dementia Recognition
Koo, J., Lee, J. H., Pyo, J., Jo, Y., & Lee, K. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-3153 · Cited by 68 · see citing works
Pappagari, R. R., Cho, J., Moro-Velázquez, L., & Dehak, N. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2587 · Cited by 68 · see citing works
Understanding spoken language through TalkBank
MacWhinney, B. (2019) · Behavior Research Methods · doi:10.3758/s13428-018-1174-9 · Cited by 66 · cited 6× · see citing works
“This study uses the ADReSS subset of the Pitt Corpus, derived from a dataset gathered longitudinally between 1983 and 1988 on a yearly basis as part of the Alzheimer Research Program at the University of Pittsburgh (Becker et al., 1994; Corey Bloom and Fleisher, 2000), and made available through DementiaBank (MacWhinn…”
BackgroundMethodInfluentialDetecting Signs of Dementia Using Word Vector Representations
Mirheidari, B., Blackburn, D. J., Walker, T., Venneri, A., Reuber, M., & Christensen, H. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-1764 · Cited by 65 · cited 1× · see citing works
“Of the studies shown in Table 3 , only Mirheidari et al. (2018) report results for embeddings derived from ASR transcription (62.5% accuracy), in contrast to the 75.6% they obtained from manual transcription.”
ResultInfluentialA Comparison of Acoustic and Linguistics Methodologies for Alzheimer’s Dementia Recognition
Cummins, N., Pan, Y., Ren, Z. X., Fritsch, J., Nallanthighal, V. S., Christensen, H., Blackburn, D. J., Schuller, B. W., Magimai.-Doss, M., Strik, H., et al. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2635 · Cited by 60 · see citing works
Vector-space topic models for detecting Alzheimer's disease
Yancheva, M., & Rudzicz, F. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1221 · Cited by 57 · cited 1× · see citing works
“Therefore, this dataset has been used in several studies, including the studies by Fraser et al. (2016), Hernández-Domínguez et al. (2018), and others (Yancheva and Rudzicz, 2016; Luz, 2017; Orimaye et al., 2017; Guo et al., 2019; Mirheidari et al., 2019b; Haider et al., 2020).”
MethodSearle, T., Ibrahim, Z. M., & Dobson, R. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2729 · Cited by 57 · see citing works
The heterogeneity of picture-supported narratives in Alzheimer’s disease
Duong, A., Giroux, F., Tardif, A., & Ska, B. (2005) · Brain and Language · doi:10.1016/j.bandl.2004.10.007 · Cited by 53 · cited 1× · see citing works
“Duong et al. (2005) ran a cluster analysis with data from picture narratives and concluded that, rather than a common profile, there were several discourse patterns that could be indicative of differences between healthy ageing and AD.”
BackgroundMartinc, M., & Pollak, S. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2202 · Cited by 52 · cited 4× · see citing works
“This is in contrast with the original implementation (Haider et al., 2020), which employed self-organising maps (SOM) clustering (Kohonen, 1990) but in line with the work done by Martinc and Pollak (2020).”
BackgroundMethodResultInfluentialSelf-citationLongitudinal Monitoring and Detection of Alzheimer's Type Dementia from Spontaneous Speech Data
Luz, S. F. (2017) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2017.41 · Cited by 50 · cited 2× · see citing works
“Therefore, this dataset has been used in several studies, including the studies by Fraser et al. (2016), Hernández-Domínguez et al. (2018), and others (Yancheva and Rudzicz, 2016; Luz, 2017; Orimaye et al., 2017; Guo et al., 2019; Mirheidari et al., 2019b; Haider et al., 2020).”
BackgroundMethodSelf-citationA Method for Analysis of Patient Speech in Dialogue for Dementia Detection
Luz, S. F., de la Fuente, S., & Albert, P. (2018) · Edinburgh Research Explorer (University of Edinburgh) · doi:10.48550/arxiv.1811.09919 · Cited by 46 · cited 2× · see citing works
“…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).”
BackgroundMethodSelf-citationMultiscale System for Alzheimer’s Dementia Recognition Through Spontaneous Speech
Edwards, E., Dognin, C., Bollepalli, B., & Singh, M. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2781 · Cited by 45 · see citing works
Taraldsen, K., Mikolaizak, A. S., Maier, A. B., Boulton, E., Aminian, K., Ancum, J. M. V., Bandinelli, S., Becker, C., Bergquist, R., Chiari, L., et al. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-023526 · Cited by 42 · see citing works
The INESC-ID Multi-Modal System for the ADReSS 2020 Challenge
Pompili, A., Rolland, T., & Abad, A. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2833 · Cited by 38 · see citing works
Detecting Alzheimer’s Disease from Continuous Speech Using Language Models
Guo, Z., Ling, Z.-H., & Li, Y. (2019) · Journal of Alzheimer s Disease · doi:10.3233/jad-190452 · Cited by 37 · see citing works
Weiner, M. W. (2005) · Alzheimer s & Dementia · doi:10.1016/j.jalz.2005.09.006 · Cited by 31 · see citing works
García, S. D. L. F., Ritchie, C. W., & Luz, S. F. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-026254 · Cited by 25 · cited 1× · see citing works
“…example of such studies is the PREVENT-ED spontaneous speech task, which has collected spontaneous dialogical speech from a group of healthy participants which includes participants genetically atrisk of AD, due to family history and apolipoprotein E (APOE) gene status (de la Fuente et al., 2019).”
BackgroundSelf-citationJonell, P., Moëll, B., Håkansson, K., Henter, G. E., Kucherenko, T., Mikheeva, O., Hagman, G., Holleman, J., Kivipelto, M., Kjellström, H., et al. (2021) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.642633 · Cited by 23 · cited 1× · see citing works
“, 2020; Mahajan and Baths, 2021), as well as eye-tracking and other sensor modalities (Jonell et al., 2021).”
BackgroundMeguro, K., Shimada, M., Someya, K., Horikawa, A., & Yamadori, A. (2001) · PubMed · Cited by 22 · see citing works
Locating case discussion segments in recorded medical team meetings
Luz, S. F. (2009) · doi:10.1145/1631127.1631131 · Cited by 21 · cited 1× · see citing works
“A more recent study by Luz et al. (2018) extracted graph-based features encoding turn-taking patterns and speech rate (Luz, 2009) from the Carolina Conversations Collection (Pope and Davis, 2011) of spontaneous interviews of AD patients and healthy controls.”
BackgroundSelf-citationWeiner, J., Frankenberg, C., Schröder, J., & Schultz, T. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003908 · Cited by 17 · cited 1× · see citing works
“This work has later been extended for prediction of development of dementia within 5 and 12 years in participants of the Interdisciplinary Longitudinal Study on Adult Development And Aging (ILSE), using a combination of acoustic and linguistic features (Weiner et al., 2019).”
BackgroundVisuospatial Function in Alzheimer's Disease and Related Disorders
Cronin‐Golomb, A. (2011) · Wiley eBooks · doi:10.1002/9781444344110.ch15 · Cited by 10 · cited 1× · see citing works
“This is manifested in the form of non-salience of visual input stimulus, and degraded attentional focus and visual search, among other disturbances (Cronin-Golomb, 2011).”
BackgroundVighetto, A. (2013) · Revue neurologique (Paris) · doi:10.1016/j.neurol.2013.08.001 · Cited by 10 · cited 2× · see citing works
“Other studies involving picture descriptions have associated AD with simultanagnosia, a disorder of attentive exploration of the spatial field (Vighetto, 2013).”
Backgroundde Ipiña, K. L., Faúndez-Zanuy, M., Solé‐Casals, J., Zelarin, F., & Calvo, P. (2016) · Smart innovation, systems and technologies · doi:10.1007/978-3-319-28109-4_7 · Cited by 7 · cited 1× · see citing works
“…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).”
Backgroundde la Fuente Garcia, S., Ritchie, C. W., & Luz, S. (2020) · Journal of Alzheimer's Disease · doi:10.3233/jad-200888 · Cited by 5 · see citing works
Self-citationChatterjee, P., Lim, W. L. F., Gupta, V. B., Sohrabi, H. R., Taddei, K., Brown, B. M., Masters, C. L., Morris, J. C., & Martins, R. N. (2014) · Alzheimer s & Dementia · doi:10.1016/j.jalz.2014.04.412 · Cited by 4 · see citing works
Mirheidari, B., Pan, Y., Walker, T., Reuber, M., Venneri, A., Blackburn, D. J., & Christensen, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00515 · Cited by 2 · cited 2× · see citing works
“Therefore, this dataset has been used in several studies, including the studies by Fraser et al. (2016), Hernández-Domínguez et al. (2018), and others (Yancheva and Rudzicz, 2016; Luz, 2017; Orimaye et al., 2017; Guo et al., 2019; Mirheidari et al., 2019b; Haider et al., 2020).”
BackgroundMethodThe natural history of Alzheimer's disease
Corey‐Bloom, J., & Fleisher, A. (2005) · CRC Press eBooks · doi:10.1201/b13239-64 · Cited by 1 · see citing works
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020) · arXiv · doi:10.48550/arxiv.2003.07082 · cited 1×
“Using the Stanza library (Qi et al., 2020) for assigning part-of-speech tags and lemmatisation, we extracted lemmas of nouns that appear at least 20 times in the test set.”
Method
Flagged first, then by citations
Research works printed but not linked: 2
- Goodglass H. Kaplan E. Barresi B. (2001). BDAE-3: Boston Diagnostic Aphasia Examination–Third Edition. Philadelphia, PA: Lippincott Williams & Wilkins.
- Pedregosa F. Varoquaux G. Gramfort A. Michel V. Thirion B. Grisel O.. (2011). Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825– 2830. Available online at: http://jmlr.org/papers/v12/pedregosa11a.html
Cited by
Sorted by citations
A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis
Xu, X., Li, J., Zhu, Z., Zhao, L., Wang, H., Song, C., Chen, Y., Zhao, Q., Yang, J., & Pei, Y. (2024) · Bioengineering · doi:10.3390/bioengineering11030219 · Cited by 242 · see citing works
Li, R., Wang, X., Lawler, K., Garg, S., Bai, Q., & Alty, J. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104030 · Cited by 144 · see citing works
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 · see citing works
“Martinc et al. (2021) employ a combination of acoustic, textual, and semantic bag-of-n-grams features for AD diagnosis based on spon-taneous speech by using a random forest algorithm with 50 trees of maximum depth 5.”
InfluentialLiu, N., Luo, K., Yuan, Z., & Chen, Y. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.772592 · Cited by 66 · see citing works
“Martinc et al. (34) also used a multimodal approach to detect AD on the ADReSS dataset, using an active data representation approach (13), combining linguistic, acoustic, and temporal features and obtaining an accuracy of 93.75%.”
MethodInfluentialDetecting dementia from speech and transcripts using transformers
Ilias, L., Askounis, D., & Psarras, J. E. (2023) · Computer Speech & Language · doi:10.1016/j.csl.2023.101485 · Cited by 51 · see citing works
“Compared with the multimodal state-of-the-art approaches, BERT+ViT+Crossmodal Attention surpasses the research works, except [43, 69], in Accuracy by 2.”
BackgroundMethodInfluentialA remote speech-based AI system to screen for early Alzheimer's disease via smartphones
Fristed, E., Skirrow, C., Meszaros, M., Lenain, R., Meepegama, U., Cappa, S., Aarsland, D., & Weston, J. (2022) · Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring · doi:10.1002/dad2.12366 · Cited by 47 · see citing works
Noninvasive automatic detection of Alzheimer's disease from spontaneous speech: a review
Qi, X., Zhou, Q., Dong, J., & Bao, W. (2023) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2023.1224723 · Cited by 42 · see citing works
“The ADR features include cluster counts, cross-modality word embeddings, pause, centroid embeddings, embedding velocity and centroid velocity, duration (Haider et al., 2019; Martinc et al., 2021).”
BackgroundSelf-Supervised ASR Models and Features for Dysarthric and Elderly Speech Recognition
Hu, S., Xie, X., Geng, M., Jin, Z., Deng, J., Li, G., Wang, Y., Cui, M., Wang, T., Meng, H. M. L., et al. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3422839 · Cited by 38 · see citing works
“…(TDNN ASR) 87.5 Wang et al. [48] Text (Conformer ASR) 91.7 Syed et al. [129] Text(manual) 91.7 Li et al. [19] Text (TDNN ASR) 88.0 Martinc et al. [130] Audio + Text (Manual) 93.8 Laguarta et al. [131] Audio + pre-trained biomarkers 93.8 Wang et al. [106] Text (CNN-TDNN ASR) 93.8 ours (Sys. 5 in…”
InfluentialLuz, S. F., Haider, F., Fromm, D., Lazarou, I., Kompatsiaris, I. Y., & MacWhinney, B. (2024) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2024.3378595 · Cited by 24 · see citing works
“We hope this might serve as a benchmark for future research on multilingual AD assessment.”
Self-citationAn explainable machine learning model of cognitive decline derived from speech
Chandler, C., Diaz‐Asper, C., Turner, R. S., Reynolds, B., & Elvevåg, B. (2023) · Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring · doi:10.1002/dad2.12516 · Cited by 24 · see citing works
“22 Given the nuance of multimodal data, it was our goal to classify cognitive decline with transparency and explainability—an important aspect of AI in clinical settings.”
BackgroundMultimodal Approaches for Alzheimer’s Detection Using Patients’ Speech and Transcript
Cai, H., Huang, X., Liu, Z., Liao, W., Dai, H., Wu, Z., Zhu, D., Ren, H., Li, Q., Liu, T., et al. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-43075-6_34 · Cited by 22 · see citing works
Parsapoor, M., Alam, M. R., & Mihailidis, A. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-023-02122-6 · Cited by 24 · see citing works
Data Augmentation for Dementia Detection in Spoken Language.
Woszczyk, D. C., Hedlikova, A., Akman, A., Demetriou, S., & Schuller, B. W. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10210 · Cited by 21 · see citing works
Leveraging Pretrained Representations With Task-Related Keywords for Alzheimer’s Disease Detection
Li, J., Song, K., Li, J., Zheng, B., Li, D., Wu, X., Liu, X., & Meng, H. M. L. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096205 · Cited by 18 · see citing works
“…methods with previous literature, we choose multiple baselines, including Luz et al. which used ComParE and Linguistic feature sets [22], Koo [12] and Syed et al. [14] which used acoustic pretrained models, and Yuan [16], Matej [17] and Yi et al. [19] which used linguistic pretrained models.”
MethodInfluentialExploiting Prompt Learning with Pre-Trained Language Models for Alzheimer’s Disease Detection
Wang, Y., Deng, J., Wang, T., Zheng, B., Hu, S., Liu, X., & Meng, H. M. L. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095993 · Cited by 19 · see citing works
“Meanwhile, [27] achieved a similarly competitive accuracy of 93.”
BackgroundAI‐based assessments of speech and language impairments in dementia
Parsapoor, M. (2023) · Alzheimer s & Dementia · doi:10.1002/alz.13395 · Cited by 15 · see citing works
Martínez‐Nicolás, I., Martínez‐Sánchez, F., Ivanova, O., & Meilán, J. J. G. (2023) · Scientific Reports · doi:10.1038/s41598-023-36804-y · Cited by 14 · see citing works
“On the other hand, AD detection in binary comparisons tends to show better results than those obtained here with accuracy, sensitivity and specificity usually above 0.90 58,59 .”
BackgroundInfluentialEarly diagnosis of Alzheimer’s Disease based on multi-attention mechanism
Yang, X., Hong, K., Zhang, D., & Wang, K. (2024) · PLoS ONE · doi:10.1371/journal.pone.0310966 · Cited by 14 · see citing works
“Martinc et al. [24] conducted an analysis of Alzheimer’s Disease diagnosis methods using audio feature engineering.”
MethodDisease Classification Model Based on Multi-Modal Feature Fusion
Wan, Z., & Shao, X.-H. (2023) · IEEE Access · doi:10.1109/access.2023.3252011 · Cited by 13 · see citing works
“Reference [8] used two modes of speech and text in the task of diagnosing Alzheimer’s disease.”
MethodLefkovitz, I., Walsh, S., Blank, L. J., Jetté, N., & Kummer, B. R. (2024) · JMIR Neurotechnology · doi:10.2196/51822 · Cited by 14 · see citing works
“The high frequency of Alzheimer disease–related NLP studies we found using BERT is expected within this context, as these studies often used the ADReSS speech dataset that consists of only 78 healthy controls and 78 patients with Alzheimer disease [28,45].”
Oh, C., Morris, R., Wang, X., & Raskin, M. S. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1129406 · Cited by 10 · see citing works
“org production impairments in people with dementia and reported the potential of acoustic analysis of prosodic features as a dementia diagnostic tool (Kato et al., 2015, 2018; Martinc et al., 2021).”
A Systematic Review of NLP for Dementia: Tasks, Datasets, and Opportunities
Peled-Cohen, L., & Reichart, R. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.35 · Cited by 13 · see citing works
“…, including silent pauses, reformulations, and context switches (Adhikari et al., 2021; Farzana et al., 2022; Williams et al., 2023), has also been identified as a strong linguistic marker, even enabling the longitudinal tracking of disease progression (Martinc et al., 2021; Robin et al., 2023).”
TaghiBeyglou, B., & Rudzicz, F. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100046 · Cited by 9 · see citing works
A comprehensive study of audio profiling: Methods, applications, challenges, and future directions
Pudasaini, A., Al-Hawawreh, M. S., Bouadjenek, M. R., Hacid, H., & Aryal, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130334 · Cited by 9 · see citing works
“…they can be used to distinguish between different speakers (speaker recognition), identify personal attributes such as emotions [47], voice pathology [48] or to identify specific sound scenes and events in an environment (like a fire alarm or bird chirping, or indoor/outdoor environments) [20].”
BackgroundA Systematic Review of Alzheimer's disease detection based on speech and natural language processing
Sevcik, A., & Rusko, M. (2022) · International Conference Radioelektronika · doi:10.1109/radioelektronika54537.2022.9764938 · Cited by 5 · see citing works
Zhou, W., Wang, Y., Yz, W., Li, X., Liu, H., Wang, H., Zhang, Z., & Huang, H. (2026) · Digital Health · doi:10.1177/20552076251412649 · Cited by 6 · see citing works
“…r e n c e s 11 , 152 , 155 , 157 , 159 , 162 , 164 , 166 ] ✓ [ S ee r e f e r e n c e s 150 , 151 , 153 , 154 , 156 , 158 , 160 , 161 , 163 , 1 65 , 167 , 189 , 196 ] A d a p t i v e f u s i o n ✓ [ S ee r e f e r e n c e s 168 , 171 , 173 , 174 , 175 , 172 , 176 , 177 , 179 , 1 80 , 181 , 186 ,…”
Pre-training and ensembling based Alzheimer’s disease detection
Xu, F., Zheng, Q., Shi, J., Yan, K., & Wang, M. (2023) · Technology and Health Care · doi:10.3233/thc-230571 · Cited by 6 · see citing works
“In addition, Martinc et al. [22] proposed a multi-modal AD detection model based on BERT, which verified the temporal interaction between the acoustics (i.e., duration, embedding velocity, centroid velocity) and the text features (i.e., bag-of-n-grams).”
Multimodal Approach for Lung Disease Classification: Fusing Chest X-Ray Images and Clinical Texts
Truong, T.-D., & Do, T. (2025) · SN Computer Science · doi:10.1007/s42979-025-04138-3 · Cited by 5 · see citing works
“The study in [37] used a multimodal approach combining acoustic and textual features to detect Alzheimer’s dementia from spontaneous speech.”
Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection
Liu, Y.-L., Feng, R., Yuan, J., & Ling, Z.-H. (2024) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp63861.2024.10799971 · Cited by 5 · see citing works
Transformer-Based Deep Learning Approaches for Speech-Based Dementia Detection: A Systematic Review
Mobtahej, P., Gouron, S., Javaheri, R., Le, D. N., El‐Khoury, A., Naing, T. H., & Sajjadi, S. A. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3595781 · Cited by 5 · see citing works
“Normalization, inwhichthefeaturedataistransformedorrescaledtoprevent inequalitiesinfeatureimportancetothemodel,isalsoaformof datapreprocessingimplementedbysomeofthepapersreviewed [43],[46],[50].”
A Review of Alzheimer’s Disease Detection from Spontaneous Speech and Text
Vrindha, M. K., Geethu, V., Anurenjan, P. R., Deepak, S., & Sreeni, K. G. (2023) · International Conference on Control, Communication and Computing (ICCC) · doi:10.1109/iccc57789.2023.10165507 · Cited by 5 · see citing works
“[10] ADReSS eGeMAPS GloVe embeddings Fusion of K-means clustering (with k=30) & RF Accuracy: 93.”
MethodFredes-Roa, C., Gutiérrez-Barría, F., Ramírez-Bruna, C., Cigarroa, I., Martella, D., Julio–Ramos, T., Méndez‐Orellana, C., & Toloza–Ramirez, D. (2022) · Neurology Perspectives · doi:10.1016/j.neurop.2022.07.007 · Cited by 2 · see citing works
Remote Inference of Cognitive Scores in ALS Patients Using a Picture Description
Agurto, C., Cecchi, G., Wen, B., Fraenkel, E., Berry, J. D., Navar, I., & Norel, R. (2023) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh60066.2023.00017 · Cited by 2 · see citing works
Alzheimer’s Disease Classification From Speech Pause Distributions With Context Information
Khatri, G., Soleimani, R., Haley, K. L., Jacks, A., & Lobaton, E. J. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782834 · Cited by 1 · see citing works
“DL models applied to dementia include multi-layer perceptrons (MLPs) [12], long short-term memory (LSTM) models [13]– [17], convolutional neural networks (CNNs) [18], and trans-formers like BERT [10], [14], [16], [19]–[23], ERNIE [23], GPT-3 [24] and the vision transformer (ViT) [19].”
Chen, S., Tan, Y. C., Hu, W., Chen, Y., Chen, L., He, Y., Yu, W., & Lü, Y. (2026) · Bioengineering · doi:10.3390/bioengineering13010073 · Cited by 1 · see citing works
“…to identify AD individuals [55]; Martinc et al. incorporated MFCC and word embedding features within a multimodal fusion framework using RF classifiers [56]; Farrús et al. employed perturbation features such as jitter and shimmer to characterize speech differences between AD and HC groups [57].”
Applications of speech analysis in diseases’ assessment, prediction and diagnosis: a scoping review
Xu, X., Zhang, Y., Niu, Q., Long, N., Li, J., Zhao, L., Yin, J., & Yang, J. (2026) · Artificial Intelligence Surgery · doi:10.20517/ais.2025.70 · Cited by 2 · see citing works
Layer-Aware Early Fusion of Acoustic and Linguistic Embeddings for Cognitive Status Classification
Novotny, K., Moro-Velázquez, L., & Mekyska, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463687 · Cited by 1 · see citing works
“Combining acoustic features with transcripts and ensembling models yields complementary gains, with simple score fusion being a common initial tactic [1, 2, 3].”
Jinming, X., Kathiresan, T., Siddiqui, A., & Vogel, A. P. (2026) · Future Neurology · doi:10.1080/14796708.2026.2692075 · Cited by 1 · see citing works
Kang, J., Li, J., Li, J., Wu, X., & Meng, H. M. L. (2024) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp63861.2024.10800483 · Cited by 1 · see citing works
Моделювання нейронної мережі для визначення стадії хвороби Альцгеймера
Pronina, O. I., & Яблокова, А. В. (2021) · Вісник Херсонського національного технічного університету · doi:10.35546/kntu2078-4481.2021.4.11
Sri Nikila., M., Babu, K. S., Kavitha, K., Sree, B. T., Kakad, S., & Muthuperumal, S. (2025) · AI-Driven Smart Healthcare for Society 5.0 · doi:10.1109/ieeeconf64992.2025.10963176
Thanh, N. N. T., Ha, H., Thanh, H. P., Thi, L. N., Trong, N. H. T., & Hoai, T. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-90197-3_37
Multi-level fusion framework for Alzheimer’s recognition using speech and textual features
Guesmi, D., Njah, H., & BenAyed, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2025.132592
Comprehensive Analysis of Multimodal Fusion Techniques for Ocular Disease Detection
M., V. K., Gupta, P., Avadhanam, R., Raj, R. N., Bhandary, S. V., Gurupur, V. P., & Mayya, V. (2026) · AI · doi:10.3390/ai7040126
AI-powered assessments for mild cognitive impairment detection: A comprehensive review
Vinesh, T., Lavanya, M. S., Arun, V., Juremi, J., Tapkire, M. D., Shashikala, B. M., & Fatin, A. M. S. (2026) · AIP conference proceedings · doi:10.1063/5.0331506
On-Device Transformer Architectures for Speech Evaluation in Neurodegenerative Disease Detection
Reimer, L. M., Pries, L., Schweizer, F., Nissen, L., & Jonas, S. M. (2026) · Computers · doi:10.3390/computers15050287
Investigating Speech as a Standalone Modality to Detect Dementia Using Deep Learning Techniques
Chakraborty, H., Batra, P., & Pillai, R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-21013-5_23
Li, R., & Wu, M. (2026) · Bioengineering · doi:10.3390/bioengineering13070748
Multimodal Speech Analysis for Early Dementia Detection Using Cross-Modal Attention Fusion
Seghroucheni, Y. Z., Hanae, B., & Minaoui, K. (2026) · International Symposium on Signal, Image, Video and Communications (ISIVC) · doi:10.1109/isivc69944.2026.11574163
“More recent transformer-based models achieved 80–85% accuracy [19], [20], comparable to our results.”
Mahmoud, M. A., Mahmoud, T. A., & Elhadad, M. K. (2026) · ICEENG International Conference for Innovations in Intelligent Computing and Cybersecurity (IICC) · doi:10.1109/iicc69623.2026.11582631
“…capture phonetic envelope variations, eGeMAPS for emotional and suprasegmental information, HNR, shimmer, and jitter to quantify voice-quality perturbations, and summary prosody measures (such as fundamental frequency statistics, speech rate, and pause ratios) that reflect fluency disruptions [8].”
Age-Inclusive Cognitive Monitoring in CUIs: How ASR Errors Affect Text-Based Dementia Biomarkers
Murphy, A., Chen, Q., Forrest, K. I., & Bennett, C. C. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816217
“Speech biomarkers can be derived from acoustic signals (e.g., prosody, pronunciation, pause structure, etc.) [27, 29, 48] or from transcripts using linguistic measures (e.g., lexical, syntactic, and discourse-level features) [5, 31].”
Zhao, Y., Huang, X., & Qi, S. (2026) · Language and Health · doi:10.1016/j.laheal.2026.100099
Cognitive Drift Mapping Using Ambient Micro-Behavioral IoT Signals in Preclinical Neurodegeneration
Aarthi, S., & Ravikumar, R. N. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0462-3.ch012
Latent Manifold Rectification for low-resource multimodal speech-based Alzheimer’s disease detection
Wang, X., Jin, Y., Huang, Y., Ma, Y., Jia, M., & Song, P. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2026.102057
Alzheimer’s multimodal diagnosis: enhancing cross-attention between speech and text
Ding, K., Hoshyar, A. N., Bhattacharya, T., & Chetty, M. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12482-5
- Authors
- Martinc, M., Haider, F., Pollak, S., & Luz, S.
- Affiliations
- Jožef Stefan Institute (SI)
- University of Edinburgh (GB)
- Corresponding author
- Martinc, Matej
- Luz, Saturnino
- Venue
- Frontiers in Aging Neuroscience
- Publisher
- Frontiers Media SA
- Published
- 2021-06-14
- Volume
- 13
- Pages
- 642647-642647
- ISSN
- 1663-4365 (ISSN-L)
- PMC
- PMC8236853
- OpenAlex
- W3170936667
- Cited by
- 55
- References
- 71
- Citations by year
- 2026: 18 · 2025: 6 · 2024: 9 · 2023: 15 · 2022: 6 · 2021: 1
- FWCI
- 5.56
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Aging Neuroscience (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- Funders
- Horizon 2020 Framework Programme
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Keywords
- Alzheimer's disease detection, dementia diagnosis, spontaneous speech, multimodal fusion, acoustic features, temporal features, decision fusion, cognitive decline monitoring, paralinguistic features
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
