A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders

Anna Favaro; Chelsie Motley; Tianyu Cao; Miguel Iglesias; Ankur Butala; Esther S. Oh; Robert D. Stevens; Jesus Villalba; Najim Dehak; Laureano Moro-Velazquez

doi:10.1109/SLT54892.2023.10022435

A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders

Anna Favaro, Chelsie Motley, Tianyu Cao, Miguel Iglesias, Ankur Butala, Esther S. Oh, Robert D. Stevens, Jesus Villalba, Najim Dehak, Laureano Moro-Velazquez

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Speech-based automatic approaches for evaluating neurological disorders (NDs) depend on feature extraction before the classification pipeline. It is preferable for these features to be interpretable to facilitate their development as diagnostic tools. This study focuses on the analysis of interpretable features obtained from the spoken responses of 88 subjects with NDs and controls (CN). Subjects with NDs have Alzheimer's disease (AD), Parkinson's disease (PD), or Parkinson's disease mimics (PDM). We configured three complementary sets of features related to cognition, speech, and language, and conducted a statistical analysis to examine which features differed between NDs and CN. Results suggested that features capturing response informativeness, reaction times, vocabulary richness, and syntactic complexity provided separability between AD and CN. Similarly, fundamental frequency variability helped differentiate PD from CN, while the number of salient informational units PDM from CN.

Original language	English (US)
Title of host publication	2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	532-539
Number of pages	8
ISBN (Electronic)	9798350396904
DOIs	https://doi.org/10.1109/SLT54892.2023.10022435
State	Published - 2023
Event	2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Doha, Qatar Duration: Jan 9 2023 → Jan 12 2023

Publication series

Name	2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

Conference

Conference	2022 IEEE Spoken Language Technology Workshop, SLT 2022
Country/Territory	Qatar
City	Doha
Period	1/9/23 → 1/12/23

Keywords

Alzheimer's disease (AD)
Parkinson's disease (PD)
artificial intelligence
biomarker
speech and language technologies

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Hardware and Architecture
Media Technology
Instrumentation
Linguistics and Language

Access to Document

10.1109/SLT54892.2023.10022435

Cite this

Favaro, A., Motley, C., Cao, T., Iglesias, M., Butala, A., Oh, E. S., Stevens, R. D., Villalba, J., Dehak, N., & Moro-Velazquez, L. (2023). A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders. In 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings (pp. 532-539). (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SLT54892.2023.10022435

A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders. / Favaro, Anna; Motley, Chelsie; Cao, Tianyu et al.
2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 532-539 (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Favaro, A, Motley, C, Cao, T, Iglesias, M, Butala, A , Oh, ES , Stevens, RD, Villalba, J, Dehak, N & Moro-Velazquez, L 2023, A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders. in 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 532-539, 2022 IEEE Spoken Language Technology Workshop, SLT 2022, Doha, Qatar, 1/9/23. https://doi.org/10.1109/SLT54892.2023.10022435

Favaro A, Motley C, Cao T, Iglesias M, Butala A , Oh ES et al. A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders. In 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 532-539. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings). doi: 10.1109/SLT54892.2023.10022435

Favaro, Anna ; Motley, Chelsie ; Cao, Tianyu et al. / A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders. 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 532-539 (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

@inproceedings{e7062b5b761a4ad58a4e207bbed25f9d,

title = "A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders",

abstract = "Speech-based automatic approaches for evaluating neurological disorders (NDs) depend on feature extraction before the classification pipeline. It is preferable for these features to be interpretable to facilitate their development as diagnostic tools. This study focuses on the analysis of interpretable features obtained from the spoken responses of 88 subjects with NDs and controls (CN). Subjects with NDs have Alzheimer's disease (AD), Parkinson's disease (PD), or Parkinson's disease mimics (PDM). We configured three complementary sets of features related to cognition, speech, and language, and conducted a statistical analysis to examine which features differed between NDs and CN. Results suggested that features capturing response informativeness, reaction times, vocabulary richness, and syntactic complexity provided separability between AD and CN. Similarly, fundamental frequency variability helped differentiate PD from CN, while the number of salient informational units PDM from CN.",

keywords = "Alzheimer's disease (AD), Parkinson's disease (PD), artificial intelligence, biomarker, speech and language technologies",

author = "Anna Favaro and Chelsie Motley and Tianyu Cao and Miguel Iglesias and Ankur Butala and Oh, {Esther S.} and Stevens, {Robert D.} and Jesus Villalba and Najim Dehak and Laureano Moro-Velazquez",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2022 IEEE Spoken Language Technology Workshop, SLT 2022 ; Conference date: 09-01-2023 Through 12-01-2023",

year = "2023",

doi = "10.1109/SLT54892.2023.10022435",

language = "English (US)",

series = "2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "532--539",

booktitle = "2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings",

}

TY - GEN

T1 - A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders

AU - Favaro, Anna

AU - Motley, Chelsie

AU - Cao, Tianyu

AU - Iglesias, Miguel

AU - Butala, Ankur

AU - Oh, Esther S.

AU - Stevens, Robert D.

AU - Villalba, Jesus

AU - Dehak, Najim

AU - Moro-Velazquez, Laureano

PY - 2023

Y1 - 2023

N2 - Speech-based automatic approaches for evaluating neurological disorders (NDs) depend on feature extraction before the classification pipeline. It is preferable for these features to be interpretable to facilitate their development as diagnostic tools. This study focuses on the analysis of interpretable features obtained from the spoken responses of 88 subjects with NDs and controls (CN). Subjects with NDs have Alzheimer's disease (AD), Parkinson's disease (PD), or Parkinson's disease mimics (PDM). We configured three complementary sets of features related to cognition, speech, and language, and conducted a statistical analysis to examine which features differed between NDs and CN. Results suggested that features capturing response informativeness, reaction times, vocabulary richness, and syntactic complexity provided separability between AD and CN. Similarly, fundamental frequency variability helped differentiate PD from CN, while the number of salient informational units PDM from CN.

AB - Speech-based automatic approaches for evaluating neurological disorders (NDs) depend on feature extraction before the classification pipeline. It is preferable for these features to be interpretable to facilitate their development as diagnostic tools. This study focuses on the analysis of interpretable features obtained from the spoken responses of 88 subjects with NDs and controls (CN). Subjects with NDs have Alzheimer's disease (AD), Parkinson's disease (PD), or Parkinson's disease mimics (PDM). We configured three complementary sets of features related to cognition, speech, and language, and conducted a statistical analysis to examine which features differed between NDs and CN. Results suggested that features capturing response informativeness, reaction times, vocabulary richness, and syntactic complexity provided separability between AD and CN. Similarly, fundamental frequency variability helped differentiate PD from CN, while the number of salient informational units PDM from CN.

KW - Alzheimer's disease (AD)

KW - Parkinson's disease (PD)

KW - artificial intelligence

KW - biomarker

KW - speech and language technologies

UR - http://www.scopus.com/inward/record.url?scp=85147798650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147798650&partnerID=8YFLogxK

U2 - 10.1109/SLT54892.2023.10022435

DO - 10.1109/SLT54892.2023.10022435

M3 - Conference contribution

AN - SCOPUS:85147798650

T3 - 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

SP - 532

EP - 539

BT - 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Spoken Language Technology Workshop, SLT 2022

Y2 - 9 January 2023 through 12 January 2023

ER -

A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this