Abstract
Language provides valuable information in dementia recognition, as language impairment is a common characteristic of early dementia. One current limitation is the lack of data due to the constraints involved in data collection. In this paper, we propose transfer learning methods that address data scarcity and involve the least amount of customization steps. We analyze language in two separate modalities: speech and linguistic information. For the first modality, we employ audio files, and for the second one, transcripts extracted from the audio files. We customize a subset of the Pitt Corpus that contains early Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) patients. Our proposed methods consist of feature-based classifiers and pre-trained models such as ResNet152, HuBERT, BERT and RoBERTa. Results show that linguistic-based transfer learning methods outperform speech-based transfer learning approaches and conventional classifiers. However, speech-based methods offer a solution that is transcription-free and end-to-end. Our main contribution is to successfully apply Automatic Speech Recognition (ASR) architectures in cognitive impairment recognition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
What Is Dementia?. Accessed 10 Oct 2021. https://www.cdc.gov/aging/dementia/index.html
World Health Organization, Dementia. September 2021. Accessed 10 Oct 2021. https://www.who.int/news-room/fact-sheets/detail/dementia
Rajan, K.B., Wilson, R.S., Weuve, J., Barnes, L.L., Evans, D.: Cognitive impairment 18 years before clinical diagnosis of Alzheimer disease dementia. Neurology 85(10), 898–904 (2015). https://doi.org/10.1212/WNL.0000000000001774, https://www.ncbi.nlm.nih.gov/pubmed/26109713
Beltrami, D., et al.: Speech analysis by natural language processing techniques: a possible tool for very early detection of cognitive decline?. Front. Aging Neurosci. 10 (2018).https://www.frontiersin.org/articles/10.3389/fnagi.2018.00369/full
Lanzi, A., Bourgeois, M., Wallace, S.: Group external memeory aid treatment for mild cognitive impairment. Alzheimer’s I & Dementia 13(7), 257 (2017). https://dx.doi.org/10.1016/j.jalz.2017.06.121
Szatloczki, G., Hoffman, I., Vincze, V., Kalman, J., Pakaski, M.: Speaking in Alzheimer’s disease, is that an early sign? importance of changes in language abilities in Alzheimer’s disease. Front. Aging Neurosci. 7 (2015). https://www.frontiersin.org/articles/10.3389/fnagi.2015.00195/full
Chakraborty, R., Pandharipande, M., Bhat, C., Kopparapu, S.K.: Identification of Dementia Using Audio Biomarkers (2020). https://arxiv.org/abs/2002.12788
de la Fuente Garcia, S., Ritchie, C.W., Luz, S.: Artificial intelligence, speech, and language processing approaches to monitoring Alzheimer’s disease: a systematic review. J. Alzheimer’s Dis. 78(4), 1547–1574 (2020). https://doi.org/10.3233/JAD-200888, https://www.ncbi.nlm.nih.gov/pubmed/33185605
Pastoriza-Dominguez, P., et al: Speech pause distribution as an early marker for Alzheimer’s disease. Speech Commun. 136, 107–117 (2022). https://doi.org/10.1101/2020, https://www.sciencedirect.com/science/article/pii/S0167639321001333.12.28.20248875
Ilias, L., Askounis, D., Psarras, J.: Detecting Dementia from Speech and Transcripts using Transformers (2021). https://arxiv.org/abs/2110.14769
Cummins, N., et al.: A comparison of acoustic and linguistics methodologies for Alzheimer’s dementia recognition. In: Proceedings Interspeech 2020, pp. 2182–86 (2020). https://doi.org/10.21437/interspeech.2020-2635, https://www.isca-speech.org/archive/interspeech_2020/cummins20_interspeech.html
Balagopalan, A., Novikova, J.: Comparing acoustic-based approaches for Alzheimer’s disease detection. In: Proceedings of Interspeech 2021 (2021). https://doi.org/10.21437/Interspeech.2021-759,https://www.isca-speech.org/archive/interspeech_2021/balagopalan21_interspeech.html
Rohanian, M., Hough, J., Purver, M.: Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer’s dementia recognition from spontaneous speech. In: Interspeech 2020, pp. 2187–2191 (2020). https://doi.org/10.21437/interspeech.2020-2721
Di Palo, F., Parde, N.: Enriching neural models with targeted features for dementia detection. In: ACL (2019). https://aclanthology.org/P19-2042/
Guo, Y., Li, C., Roan, C., Pakhomov, S., Cohen, T.: Crossing the cookie theft corpus chasm: applying what BERT learns from outside data to the ADReSS challenge dementia detection task. Front. Comput. Sci. (Lausanne), 3 (2021). https://doi.org/10.3389/fcomp.2021.642517, https://doaj.org/article/417d2905f8ed446884c6ff7f860e4453
Campbell, E.L. et al.: Alzheimer’s Dementia Detection from Audio and Text Modalities (2020). https://arxiv.org/abs/2008.04617
Balagopalan, A., Eyre, B., Rudzicz, F., Novikova, J.: To BERT or Not To BERT: comparing speech and language-based approaches for Alzheimer’s disease detection. In: Proceedings Interspeech 2020 (2020). https://arxiv.org/abs/2008.01551. https://doi.org/10.21437/Interspeech.2020-2557
Clarke, N., Barrick, T.R., Garrard, P.: A comparison of connected speech tasks for detecting early Alzheimer’s disease and mild cognitive impairment using natural language processing and machine learning. Front. Comput. Sci. (Lausanne), 3 (2021). https://doi.org/10.3389/fcomp.2021.634360, https://doaj.org/article/ef7ae92f93544eefacafacbab4dfa2cd
Schuller, B., et al.: The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. In: Proceedings of Interspeech 2013 (2013). https://doi.org/10.21437/Interspeech.2013-56, https://www.isca-speech.org/archive/interspeech_2013/schuller13_interspeech.html
MacWhinney, B.: The Childes Project. Taylor and Francis (2014)
de Lira, J.O., Minnet, T.S., Ferreira P.H., Ortiz, K.Z.: Analysis of word number and content in discourse of patients with mild to moderate Alzheimer’s disease. Dementia Neuropsychol. 8(3), 260–265 (2014). https://doi.org/10.1590/S1980-57642014DN83000010, https://www.ncbi.nlm.nih.gov/pubmed/29213912.57642014DN83000010
Balagopalan, A., Eyre, B., Rudzicz, F., Novikova, J.: To BERT or Not To BERT: comparing speech and language-based approaches for Alzheimer’s disease detection. In: Proceedings Interspeech 2020 (2020). https://doi.org/10.21437/Interspeech.2020-2557, https://arxiv.org/abs/2008.01551
Liu, Y., et al.: RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019). https://arxiv.org/abs/1907.11692
Becker, J.T., Boller, F., Lopez, O.L., Saxton, J., McGonigle, K.L.: The natural history of Alzheimer’s disease: description of study cohort and accuracy of diagnosis. Arch. Neurol. 51(6), 585–594 (1994). https://dementia.talkbank.org/access/0docs/Becker1994.pdf
Giannakopoulos, T.: pyAudioAnalysis: an open-source python library for audio signal analysis. PloS One 10(12) (2015). https://doi.org/10.1371/journal.pone.0144610, https://www.ncbi.nlm.nih.gov/pubmed/26656189
Luz, S., Haider, F., de la Fuente, S., Fromm, D., MacWhinney, B.: Alzheimer’s dementia recognition through spontaneous speech: the ADReSS challenge. In: Proceedings Interspeech, pp. 2172–2176 (2020). https://doi.org/10.21437/Interspeech.2020-2571
Luz, S., Haider, F., de la Fuente, S., Fromm, D., MacWhinney, B.: Detecting cognitive decline using speech only: the ADReSSo Challenge (2021). https://doi.org/10.1101/2021.03.24.21254263, https://arxiv.org/abs/2104.09356
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Monica, G.M., Rafael, M.T. (2022). A Comparison of Feature-based Classifiers and Transfer Learning Approaches for Cognitive Impairment Recognition in Language. In: Ferrández Vicente, J.M., Álvarez-Sánchez, J.R., de la Paz López, F., Adeli, H. (eds) Artificial Intelligence in Neuroscience: Affective Analysis and Health Applications. IWINAC 2022. Lecture Notes in Computer Science, vol 13258. Springer, Cham. https://doi.org/10.1007/978-3-031-06242-1_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-06242-1_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06241-4
Online ISBN: 978-3-031-06242-1
eBook Packages: Computer ScienceComputer Science (R0)