Cargando…
Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech
Dementia, a prevalent disorder of the brain, has negative effects on individuals and society. This paper concerns using Spontaneous Speech (ADReSS) Challenge of Interspeech 2020 to classify Alzheimer's dementia. We used (1) VGGish, a deep, pretrained, Tensorflow model as an audio feature extrac...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7907518/ https://www.ncbi.nlm.nih.gov/pubmed/33643116 http://dx.doi.org/10.3389/fpsyg.2020.623237 |
_version_ | 1783655513432522752 |
---|---|
author | Chlasta, Karol Wołk, Krzysztof |
author_facet | Chlasta, Karol Wołk, Krzysztof |
author_sort | Chlasta, Karol |
collection | PubMed |
description | Dementia, a prevalent disorder of the brain, has negative effects on individuals and society. This paper concerns using Spontaneous Speech (ADReSS) Challenge of Interspeech 2020 to classify Alzheimer's dementia. We used (1) VGGish, a deep, pretrained, Tensorflow model as an audio feature extractor, and Scikit-learn classifiers to detect signs of dementia in speech. Three classifiers (LinearSVM, Perceptron, 1NN) were 59.1% accurate, which was 3% above the best-performing baseline models trained on the acoustic features used in the challenge. We also proposed (2) DemCNN, a new PyTorch raw waveform-based convolutional neural network model that was 63.6% accurate, 7% more accurate then the best-performing baseline linear discriminant analysis model. We discovered that audio transfer learning with a pretrained VGGish feature extractor performs better than the baseline approach using automatically extracted acoustic features. Our DepCNN exhibits good generalization capabilities. Both methods presented in this paper offer progress toward new, innovative, and more effective computer-based screening of dementia through spontaneous speech. |
format | Online Article Text |
id | pubmed-7907518 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-79075182021-02-27 Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech Chlasta, Karol Wołk, Krzysztof Front Psychol Psychology Dementia, a prevalent disorder of the brain, has negative effects on individuals and society. This paper concerns using Spontaneous Speech (ADReSS) Challenge of Interspeech 2020 to classify Alzheimer's dementia. We used (1) VGGish, a deep, pretrained, Tensorflow model as an audio feature extractor, and Scikit-learn classifiers to detect signs of dementia in speech. Three classifiers (LinearSVM, Perceptron, 1NN) were 59.1% accurate, which was 3% above the best-performing baseline models trained on the acoustic features used in the challenge. We also proposed (2) DemCNN, a new PyTorch raw waveform-based convolutional neural network model that was 63.6% accurate, 7% more accurate then the best-performing baseline linear discriminant analysis model. We discovered that audio transfer learning with a pretrained VGGish feature extractor performs better than the baseline approach using automatically extracted acoustic features. Our DepCNN exhibits good generalization capabilities. Both methods presented in this paper offer progress toward new, innovative, and more effective computer-based screening of dementia through spontaneous speech. Frontiers Media S.A. 2021-02-12 /pmc/articles/PMC7907518/ /pubmed/33643116 http://dx.doi.org/10.3389/fpsyg.2020.623237 Text en Copyright © 2021 Chlasta and Wołk. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Psychology Chlasta, Karol Wołk, Krzysztof Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech |
title | Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech |
title_full | Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech |
title_fullStr | Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech |
title_full_unstemmed | Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech |
title_short | Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech |
title_sort | towards computer-based automated screening of dementia through spontaneous speech |
topic | Psychology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7907518/ https://www.ncbi.nlm.nih.gov/pubmed/33643116 http://dx.doi.org/10.3389/fpsyg.2020.623237 |
work_keys_str_mv | AT chlastakarol towardscomputerbasedautomatedscreeningofdementiathroughspontaneousspeech AT wołkkrzysztof towardscomputerbasedautomatedscreeningofdementiathroughspontaneousspeech |