Identifying Mild Cognitive Impairment and mild Alzheimer's disease based on spontaneous speech using ASR and linguistic features

Gábor Gosztolya, Veronika Vincze, László Tóth, M. Pákáski, J. Kálmán, Ildikó Hoffmann

Research output: Contribution to journalArticle

Abstract

Alzheimer's disease (AD) is a neurodegenerative disorder that develops for years before clinical manifestation, while mild cognitive impairment is clinically considered as a prodromal stage of AD. For both types of neurodegenerative disorders, early diagnosis is crucial for the timely treatment and to decelerate progression. Unfortunately, the current diagnostic solutions are time-consuming. Here, we seek to exploit the observation that these illnesses frequently disturb the mental and linguistic functions, which might be detected from the spontaneous speech produced by the patient. First, we present an automatic speech recognition based procedure for the extraction of a special set of acoustic features. Second, we present a linguistic feature set that is extracted from the transcripts of the same speech signals. The usefulness of the two feature sets is evaluated via machine learning experiments, where our goal is not only to differentiate between the patients and the healthy control group, but also to tell apart Alzheimer's patients from those with mild cognitive impairment. Our results show that based on only the acoustic features, we are able to separate the various groups with accuracy scores between 74–82%. We attained similar accuracy scores when using only the linguistic features. With the combination of the two types of features, the accuracy scores rise to between 80–86%, and the corresponding F1 values also fall between 78–86%. We hope that with the full automation of the processing chain, our method can serve as the basis of an automatic screening test in the future.

LanguageEnglish
Pages181-197
Number of pages17
JournalComputer Speech and Language
Volume53
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Alzheimer's Disease
Linguistics
Disorder
Acoustics
Decelerate
Automatic Speech Recognition
Speech Signal
Differentiate
Speech recognition
Progression
Automation
Screening
Learning systems
Diagnostics
Machine Learning
Processing
Experiment
Speech
Experiments

Keywords

  • Alzheimer's disease
  • Automatic screening
  • Automatic speech recognition
  • Classifier combination
  • Mild cognitive impairment
  • Natural language processing

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Human-Computer Interaction

Cite this

Identifying Mild Cognitive Impairment and mild Alzheimer's disease based on spontaneous speech using ASR and linguistic features. / Gosztolya, Gábor; Vincze, Veronika; Tóth, László; Pákáski, M.; Kálmán, J.; Hoffmann, Ildikó.

In: Computer Speech and Language, Vol. 53, 01.01.2019, p. 181-197.

Research output: Contribution to journalArticle

@article{67b46d732c3b40da8ae893f533840d1c,
title = "Identifying Mild Cognitive Impairment and mild Alzheimer's disease based on spontaneous speech using ASR and linguistic features",
abstract = "Alzheimer's disease (AD) is a neurodegenerative disorder that develops for years before clinical manifestation, while mild cognitive impairment is clinically considered as a prodromal stage of AD. For both types of neurodegenerative disorders, early diagnosis is crucial for the timely treatment and to decelerate progression. Unfortunately, the current diagnostic solutions are time-consuming. Here, we seek to exploit the observation that these illnesses frequently disturb the mental and linguistic functions, which might be detected from the spontaneous speech produced by the patient. First, we present an automatic speech recognition based procedure for the extraction of a special set of acoustic features. Second, we present a linguistic feature set that is extracted from the transcripts of the same speech signals. The usefulness of the two feature sets is evaluated via machine learning experiments, where our goal is not only to differentiate between the patients and the healthy control group, but also to tell apart Alzheimer's patients from those with mild cognitive impairment. Our results show that based on only the acoustic features, we are able to separate the various groups with accuracy scores between 74–82{\%}. We attained similar accuracy scores when using only the linguistic features. With the combination of the two types of features, the accuracy scores rise to between 80–86{\%}, and the corresponding F1 values also fall between 78–86{\%}. We hope that with the full automation of the processing chain, our method can serve as the basis of an automatic screening test in the future.",
keywords = "Alzheimer's disease, Automatic screening, Automatic speech recognition, Classifier combination, Mild cognitive impairment, Natural language processing",
author = "G{\'a}bor Gosztolya and Veronika Vincze and L{\'a}szl{\'o} T{\'o}th and M. P{\'a}k{\'a}ski and J. K{\'a}lm{\'a}n and Ildik{\'o} Hoffmann",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.csl.2018.07.007",
language = "English",
volume = "53",
pages = "181--197",
journal = "Computer Speech and Language",
issn = "0885-2308",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Identifying Mild Cognitive Impairment and mild Alzheimer's disease based on spontaneous speech using ASR and linguistic features

AU - Gosztolya, Gábor

AU - Vincze, Veronika

AU - Tóth, László

AU - Pákáski, M.

AU - Kálmán, J.

AU - Hoffmann, Ildikó

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Alzheimer's disease (AD) is a neurodegenerative disorder that develops for years before clinical manifestation, while mild cognitive impairment is clinically considered as a prodromal stage of AD. For both types of neurodegenerative disorders, early diagnosis is crucial for the timely treatment and to decelerate progression. Unfortunately, the current diagnostic solutions are time-consuming. Here, we seek to exploit the observation that these illnesses frequently disturb the mental and linguistic functions, which might be detected from the spontaneous speech produced by the patient. First, we present an automatic speech recognition based procedure for the extraction of a special set of acoustic features. Second, we present a linguistic feature set that is extracted from the transcripts of the same speech signals. The usefulness of the two feature sets is evaluated via machine learning experiments, where our goal is not only to differentiate between the patients and the healthy control group, but also to tell apart Alzheimer's patients from those with mild cognitive impairment. Our results show that based on only the acoustic features, we are able to separate the various groups with accuracy scores between 74–82%. We attained similar accuracy scores when using only the linguistic features. With the combination of the two types of features, the accuracy scores rise to between 80–86%, and the corresponding F1 values also fall between 78–86%. We hope that with the full automation of the processing chain, our method can serve as the basis of an automatic screening test in the future.

AB - Alzheimer's disease (AD) is a neurodegenerative disorder that develops for years before clinical manifestation, while mild cognitive impairment is clinically considered as a prodromal stage of AD. For both types of neurodegenerative disorders, early diagnosis is crucial for the timely treatment and to decelerate progression. Unfortunately, the current diagnostic solutions are time-consuming. Here, we seek to exploit the observation that these illnesses frequently disturb the mental and linguistic functions, which might be detected from the spontaneous speech produced by the patient. First, we present an automatic speech recognition based procedure for the extraction of a special set of acoustic features. Second, we present a linguistic feature set that is extracted from the transcripts of the same speech signals. The usefulness of the two feature sets is evaluated via machine learning experiments, where our goal is not only to differentiate between the patients and the healthy control group, but also to tell apart Alzheimer's patients from those with mild cognitive impairment. Our results show that based on only the acoustic features, we are able to separate the various groups with accuracy scores between 74–82%. We attained similar accuracy scores when using only the linguistic features. With the combination of the two types of features, the accuracy scores rise to between 80–86%, and the corresponding F1 values also fall between 78–86%. We hope that with the full automation of the processing chain, our method can serve as the basis of an automatic screening test in the future.

KW - Alzheimer's disease

KW - Automatic screening

KW - Automatic speech recognition

KW - Classifier combination

KW - Mild cognitive impairment

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85052907114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052907114&partnerID=8YFLogxK

U2 - 10.1016/j.csl.2018.07.007

DO - 10.1016/j.csl.2018.07.007

M3 - Article

VL - 53

SP - 181

EP - 197

JO - Computer Speech and Language

T2 - Computer Speech and Language

JF - Computer Speech and Language

SN - 0885-2308

ER -