Abstract
The World Health Organization estimates that 50 million people are currently living with dementia worldwide and this figure will almost triple by 2050. Current pharmacological treatments are only symptomatic, and drugs or other therapies are ineffective in slowing down or curing the neurodegenerative process at the basis of dementia. Therefore, early detection of cognitive decline is of the utmost importance to respond significantly and deliver preventive interventions. Recently, the researchers showed that speech alterations might be one of the earliest signs of cognitive defect, observable well in advance before other cognitive deficits become manifest. In this article, we propose a full automated method able to classify the audio file of the subjects according to the progress level of the pathology. In particular, we trained a specific type of artificial neural network, called autoencoder, using the visual representation of the audio signal of the subjects, that is, the spectrogram. Moreover, we used a data augmentation approach to overcome the problem of the large amount of annotated data usually required during the training phase, which represents one of the most major obstacles in deep learning. We evaluated the proposed method using a dataset of 288 audio files from 96 subjects: 48 healthy controls and 48 cognitively impaired participants. The proposed method obtained good classification results compared to the state-of-the-art neuropsychological screening tests and, with an accuracy of 90.57%, outperformed the methods based on manual transcription and annotation of speech.
- [1] . 2009. Connectionist diagnosis of lexical disorders in aphasia. Aphasiology 23, 11 (2009), 1353–1378.Google Scholar
- [2] . 2019. Automatic speech analysis to early detect functional cognitive decline in elderly population. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’19). IEEE, 212–216.Google Scholar
- [3] . 2016. Automatic identification of mild cognitive impairment through the analysis of Italian spontaneous speech productions. In Proceedings of the 10th International Conference on Language Resources and Evaluation
(LREC’16) . 2086–2093.Google Scholar - [4] . 2018. Speech analysis by natural language processing techniques: A possible tool for very early detection of cognitive decline?Frontiers in Aging Neuroscience 10 (2018), 369.Google Scholar
Cross Ref
- [5] . 2018. Predicting frailty condition in elderly using multidimensional socioclinical databases. Proceedings of the IEEE 106, 4 (2018), 723–737.Google Scholar
- [6] . 2017. Connected speech in neurodegenerative language disorders: A review. Frontiers in Psychology 8 (2017), 269.Google Scholar
- [7] . 2011. Memory Loss E-Book: A Practical Guide for Clinicians. Elsevier Health Sciences.Google Scholar
- [8] . 2015. Should we screen for cognitive decline and dementia?Maturitas 82, 1 (2015), 28–35.Google Scholar
- [9] . 2020. Linguistic features and automatic classifiers for identifying mild cognitive impairment and dementia. Computer Speech & Language 65 (2020), 101113.Google Scholar
Cross Ref
- [10] . 1996. Esame Del Linguaggio-II. OS. Retrieved on August 28, 2021 from https://www.giuntipsy.it/catalogo/test/esame-del-linguaggio-ii.Google Scholar
- [11] . 2016. Novel verbal fluency scores and structural brain imaging for prediction of cognitive outcome in mild cognitive impairment. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring 2 (2016), 113–122.Google Scholar
- [12] . 2018. CNN+LSTM architecture for speech emotion recognition with data augmentation. arXiv:1802.05630. https://arxiv.org/abs/1802.05630Google Scholar
- [13] . 2009. Progression of mild cognitive impairment to dementia in clinic- vs community-based cohorts. Archives of Neurology 66, 9 (2009), 1151–1157.Google Scholar
Cross Ref
- [14] . 1975. “Mini-mental state”: A practical method for grading the cognitive state of patients for the clinician. Journal of Psychiatric Research 12, 3 (1975), 189–198.Google Scholar
Cross Ref
- [15] . 2018. Automated syntactic analysis of language abilities in persons with mild and subjective cognitive impairment.. In MIE. 705–709.Google Scholar
- [16] . 2018. Improving the sensitivity and specificity of MCI screening with linguistic information. In LREC Workshop: RaPID-2.Google Scholar
- [17] . 2019. Multilingual word embeddings for the assessment of narrative speech in mild cognitive impairment. Computer Speech & Language 53 (2019), 121–139.Google Scholar
- [18] . 2017. An analysis of eye-movements during reading for the detection of mild cognitive impairment. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 1016–1026.Google Scholar
- [19] . 2019. Predicting MCI status from multimodal language data using cascaded classifiers. Frontiers in Aging Neuroscience 11 (2019), 205.Google Scholar
- [20] . 2017. auDeep: Unsupervised learning of representations from audio with deep recurrent neural networks. The Journal of Machine Learning Research 18, 1 (2017), 6340–6344. Google Scholar
Digital Library
- [21] . 2019. Identifying mild cognitive impairment and mild Alzheimer’s disease based on spontaneous speech using ASR and linguistic features. Computer Speech & Language 53 (2019), 181–197.Google Scholar
Cross Ref
- [22] . 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv:1412.5567. https://arxiv.org/abs/1412.5567Google Scholar
- [23] . 2013. Vocal tract length perturbation (VTLP) improves speech recognition. In Proceedings of the ICML Workshop on Deep Learning for Audio, Speech and Language, Vol. 117.Google Scholar
- [24] . 2014. Aided diagnosis of dementia type through computer-based analysis of spontaneous speech. In Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality. 27–37.Google Scholar
- [25] . 2013. Elastic spectral distortion for low resource speech recognition with deep neural networks. In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding. IEEE, 309–314.Google Scholar
- [26] . 2017. Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home. Interspeech 2017 (2017), 379–383.Google Scholar
- [27] . 2015. Audio augmentation for speech recognition. In 16th Annual Conference of the International Speech Communication Association.Google Scholar
- [28] . 2018. Use of speech analyses within a mobile application for the assessment of cognitive impairment in elderly people. Current Alzheimer Research 15, 2 (2018), 120–129.Google Scholar
- [29] . 2015. Automatic speech analysis for the assessment of patients with predementia and Alzheimer’s disease. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring 1, 1 (2015), 112–124.Google Scholar
- [30] . 2020. Automated assessment of psychiatric disorders using speech: A systematic review. Laryngoscope Investigative Otolaryngology 5, 1 (2020), 96–116.Google Scholar
Cross Ref
- [31] . 2016. DepAudioNet: An efficient deep model for audio based depression classification. In Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge. 35–42. Google Scholar
Digital Library
- [32] . 2012. Acoustic markers associated with impairment in language processing in Alzheimer’s disease. The Spanish Journal of Psychology 15, 2 (2012), 487–494.Google Scholar
- [33] . 2009. A meta-analysis of the accuracy of the mini-mental state examination in the detection of dementia and mild cognitive impairment. Journal of Psychiatric Research 43, 4 (2009), 411–431.Google Scholar
Cross Ref
- [34] . 2017. Global action plan on the public health response to dementia 2017–2025. Retrieved on August 28, 2021 from https://www.who.int/publications/i/item/global-action-plan-on-the-public-health-response-to-dementia-2017---2025.Google Scholar
- [35] . 2019. SpecAugment: A simple data augmentation method for automatic speech recognition. arXiv:1904.08779. https://arxiv.org/abs/1904.08779Google Scholar
- [36] . 2011. Clinical practice. mild cognitive impairment.The New England Journal of Medicine 364, 23 (2011), 2227.Google Scholar
- [37] . 2018. Data augmentation for robust keyword spotting under playback interference. arXiv:1808.00563. https://arxiv.org/abs/1808.00563Google Scholar
- [38] . 2018. Identification of mild cognitive impairment from speech in Swedish using deep sequential neural networks. Frontiers in Neurology 9 (2018), 975.Google Scholar
- [39] . [n.d.]. Effects of mild cognitive impairment on vowel duration. Retrieved on August 28, 2021 from https://gup.ub.gu.se/publication/270215?lang=en.Google Scholar
- [40] . 2018. A speech recognition-based solution for the automatic detection of mild cognitive impairment from spontaneous speech. Current Alzheimer Research 15, 2 (2018), 130–138.Google Scholar
- [41] . 2016. Detecting mild cognitive impairment by exploiting linguistic information from transcripts. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Berlin, Germany, August 2016. Association for Computational Linguistics, 181–187.Google Scholar
- [42] . 2018. Clinical text annotation-What factors are associated with the cost of time?. In AMIA Annual Symposium Proceedings, Vol. 2018. American Medical Informatics Association, 1552.Google Scholar
- [43] . 2017. The worldwide costs of dementia 2015 and comparisons with 2010. Alzheimer’s & Dementia 13, 1 (2017), 1–7.Google Scholar
- [44] . 2015. Cognitive impairment prediction in the elderly based on vocal biomarkers. In 16th Annual Conference of the International Speech Communication Association.Google Scholar
Index Terms
Automatic Speech Classifier for Mild Cognitive Impairment and Early Dementia
Recommendations
Automatic screening of mild cognitive impairment and Alzheimer’s disease by means of posterior-thresholding hesitation representation
AbstractDementia is a chronic or progressive clinical syndrome, characterized by the deterioration of problem-solving skills, memory and language. In Mild Cognitive Impairment (MCI), which is often considered to be the prodromal stage of ...
Highlights- Automatic diagnosis of dementia using a non-invasive way: the speech of the patient.
Classification of dementia types from cognitive profiles data
ECMLPKDD'06: Proceedings of the 10th European Conference on Principles and Practice of Knowledge Discovery in DatabasesThe Cognitive Drug Research (CDR) system is specifically validated for dementia assessment; it consists of a series of computerized tests, which assess the cognitive faculties of the patient to derive a cognitive profile. We use six different ...
A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimer's disease and mild cognitive impairment
Population aging has been occurring as a global phenomenon with heterogeneous consequences in both developed and developing countries. Neurodegenerative diseases, such as Alzheimer@?s Disease (AD), have high prevalence in the elderly population. Early ...






Comments