Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech

被引:19
作者
Chlasta, Karol [1 ,2 ]
Wolk, Krzysztof [1 ]
机构
[1] Polish Japanese Acad Informat Technol, Dept Comp Sci, Warsaw, Poland
[2] SWPS Univ Social Sci & Humanities, Inst Psychol, Warsaw, Poland
关键词
dementia detection; prosodic analysis; affective computing; transfer learning; convolutional neural network; machine learning; speech technology; mental health monitoring; ALZHEIMERS-DISEASE; DEPRESSION; AUDIO;
D O I
10.3389/fpsyg.2020.623237
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
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.
引用
收藏
页数:6
相关论文
共 39 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]  
[Anonymous], 2016, YOUTUBE 8M A LARGE S
[3]  
Baldas V, 2011, L N INST COMP SCI SO, V55, P105
[4]   Epidemiology of multimorbidity and implications for health care, research, and medical education: a cross-sectional study [J].
Barnett, Karen ;
Mercer, Stewart W. ;
Norbury, Michael ;
Watt, Graham ;
Wyke, Sally ;
Guthrie, Bruce .
LANCET, 2012, 380 (9836) :37-43
[5]  
Bisong E., 2019, Building machine learning and deep learning models on Google cloud platform: a comprehensive guide for beginners, P59, DOI [DOI 10.1007/978-1-4842-4470-8_19, DOI 10.1007/978-1-4842-4470-8_7]
[6]   Analysis of spontaneous, conversational speech in dementia of Alzheimer type: Evaluation of an objective technique for analysing lexical performance [J].
Bucks, RS ;
Singh, S ;
Cuerden, JM ;
Wilcock, GK .
APHASIOLOGY, 2000, 14 (01) :71-91
[7]   Is depression in elderly people followed by dementia? A retrospective cohort study based in general practice [J].
Buntinx, F ;
Kester, A ;
Bergers, J ;
Knottnerus, JA .
AGE AND AGEING, 1996, 25 (03) :231-233
[8]   A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine [J].
Cao, LJ ;
Chua, KS ;
Chong, WK ;
Lee, HP ;
Gu, QM .
NEUROCOMPUTING, 2003, 55 (1-2) :321-336
[9]   A Feature Study for Classification-Based Speech Separation at Low Signal-to-Noise Ratios [J].
Chen, Jitong ;
Wang, Yuxuan ;
Wang, DeLiang .
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (12) :1993-2002
[10]   Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis [J].
Cheplygina, Veronika ;
de Bruijne, Marleen ;
Pluim, Josien P. W. .
MEDICAL IMAGE ANALYSIS, 2019, 54 :280-296