AI classification of respiratory illness through vocal biomarkers and a bespoke articulatory speech protocol

Tim Bashford; Hok Shing Lau; Mark Huntly; Nathan Morgan; Adesua  Iyenoma; Tom Powell; Biao Zeng

AI classification of respiratory illness through vocal biomarkers and a bespoke articulatory speech protocol

Tim Bashford^*, Hok Shing Lau, Mark Huntly, Nathan Morgan, Adesua Iyenoma, Tom Powell, Biao Zeng

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

115 Downloads (Pure)

Abstract

Speech biomarkers represent a powerful indicator for detecting, monitoring and categorising neurological, psychological , pathological and pulmonary conditions. Facilitated by advances in computational power and artificial intelligence (AI) techniques, we present a novel ecosystem for data acquisition , analysis and storage, using an articulatory speech task. By automatically segmenting, aligning and extracting features from the vocal recordings, we present a feature extraction pipeline toward the classification of pathological conditions, specifically respiratory disease through recorded voice. Data is stored within a Trusted Research Environment, for which this work also presents a range of ethical considerations.

Original language	English
Article number	13
Number of pages	5
Journal	International Journal of Simulation, Systems, Science and Technology
Volume	25
Issue number	1
Publication status	Published - Mar 2024
Event	UKSim-AMSS: International Conference on Mathematical/Analytical Modelling and Computer Simulation - Emmanuel College, Cambridge, United Kingdom Duration: 26 Mar 2024 → 28 Mar 2024 Conference number: 26th

Keywords

Speech biomarkers
respiratory disease
artificial intelligence
speech breathing

Access to Document

AI classification of respiratory illness through vocal biomarkers and a bespoke articulatory speech protocolFinal published version, 923 KB

https://ijssst.info/Vol-25/No-1/paper13.pdf

2 Conference contribution
1 Paper
1 Article

Speech Breathing Under Cognitive Load: A Pilot Study of English and Arabic Bilingual Adaptation Using the Helicopter Test
Chadli, H., Zeng, B. & Zhou, X., 20 Aug 2025, (E-pub ahead of print) Artificial Intelligence in Healthcare. Cafolla, D., Rittman, T. & Ni, H. (eds.). 1 ed. Springer, Vol. 1. p. 200-212 12 p. (Lecture Notes in Computer Science; vol. 16038).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders
Lau, H. S., Huntly, M., Morgan, N., Iyenoma, A., Zeng, B. & Bashford, T., 14 Aug 2024, Artificial Intelligence in Healthcare - 1st International Conference, AIiH 2024, Proceedings: First International Conference, AIiH 2024, Swansea, UK, September 4–6, 2024, Proceedings, Part I. Xie, X., Powathil, G., Styles, I. & Ceccarelli, M. (eds.). Springer, p. 59-72 14 p. (Lecture Notes in Computer Science; vol. 14975).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
23 Downloads (Pure)
Word or Phoneme? To Optimise Prosodic Features to Predict Lung Function with Helicopter Task
Zeng, B., Lau, H. S., Huntly, M., Bashford, T., Morgan, N., Williams, C. & Game, L., Sept 2024, (Accepted/In press).
Research output: Contribution to conference › Paper › peer-review

Open Access
File
Exploring the Acoustic and Prosodic Features of a Lung Function Sensitive Repeated-word Speech Articulation Test
Zeng, B., Williams, E. M., Owen, C., Zhang, C., Davies, S., Evans, K. & Preudhomme, S.-R., 30 Aug 2023, In: Frontiers in Psychology. 14, 8 p., 1167902.
Research output: Contribution to journal › Article › peer-review

Open Access
File
46 Downloads (Pure)

1 Participation in conference
1 Organising an event
1 Invited talk

INTERSPEECH 2024
Zeng, B. (Organiser), Zhou, X. (Speaker), Powell, T. (Speaker), Bashford, T. (Speaker), Huntly, M. (Speaker), Morgan, N. (Speaker) & Salter, R. (Speaker)
1 Sept 2024
Activity: Participating in or organising an event › Participation in conference
Helicopter task: exploring the acoustic, prosodic and breathing features of a lung function sensitive repeated-word speech articulation test
Zeng, B. (Invited speaker)
30 Jun 2023
Activity: Talk or presentation › Invited talk
Speech Breathing Workshop
Zeng, B. (Organiser), Davies, S. (Organiser) & Owen, C. (Organiser)
6 Jun 2023
Activity: Participating in or organising an event › Organising an event

File

Cite this

@article{5c38352ee4244e74be59239ac1ce06c3,

title = "AI classification of respiratory illness through vocal biomarkers and a bespoke articulatory speech protocol",

abstract = "Speech biomarkers represent a powerful indicator for detecting, monitoring and categorising neurological, psychological , pathological and pulmonary conditions. Facilitated by advances in computational power and artificial intelligence (AI) techniques, we present a novel ecosystem for data acquisition , analysis and storage, using an articulatory speech task. By automatically segmenting, aligning and extracting features from the vocal recordings, we present a feature extraction pipeline toward the classification of pathological conditions, specifically respiratory disease through recorded voice. Data is stored within a Trusted Research Environment, for which this work also presents a range of ethical considerations.",

keywords = "Speech biomarkers, respiratory disease, artificial intelligence, speech breathing",

author = "Tim Bashford and Lau, {Hok Shing} and Mark Huntly and Nathan Morgan and Adesua Iyenoma and Tom Powell and Biao Zeng",

note = "Non-OA DOI for records - 10.5013/IJSSST.a.25.01.13; UKSim-AMSS : International Conference on Mathematical/Analytical Modelling and Computer Simulation, UKSim2024 ; Conference date: 26-03-2024 Through 28-03-2024",

year = "2024",

month = mar,

language = "English",

volume = "25",

journal = "International Journal of Simulation, Systems, Science and Technology",

issn = "1473-804X",

publisher = "United Kingdom Simulation Society",

number = "1",

}

TY - JOUR

T1 - AI classification of respiratory illness through vocal biomarkers and a bespoke articulatory speech protocol

AU - Bashford, Tim

AU - Lau, Hok Shing

AU - Huntly, Mark

AU - Morgan, Nathan

AU - Iyenoma, Adesua

AU - Powell, Tom

AU - Zeng, Biao

N1 - Conference code: 26th

PY - 2024/3

Y1 - 2024/3

N2 - Speech biomarkers represent a powerful indicator for detecting, monitoring and categorising neurological, psychological , pathological and pulmonary conditions. Facilitated by advances in computational power and artificial intelligence (AI) techniques, we present a novel ecosystem for data acquisition , analysis and storage, using an articulatory speech task. By automatically segmenting, aligning and extracting features from the vocal recordings, we present a feature extraction pipeline toward the classification of pathological conditions, specifically respiratory disease through recorded voice. Data is stored within a Trusted Research Environment, for which this work also presents a range of ethical considerations.

AB - Speech biomarkers represent a powerful indicator for detecting, monitoring and categorising neurological, psychological , pathological and pulmonary conditions. Facilitated by advances in computational power and artificial intelligence (AI) techniques, we present a novel ecosystem for data acquisition , analysis and storage, using an articulatory speech task. By automatically segmenting, aligning and extracting features from the vocal recordings, we present a feature extraction pipeline toward the classification of pathological conditions, specifically respiratory disease through recorded voice. Data is stored within a Trusted Research Environment, for which this work also presents a range of ethical considerations.

KW - Speech biomarkers

KW - respiratory disease

KW - artificial intelligence

KW - speech breathing

M3 - Conference article

SN - 1473-804X

VL - 25

JO - International Journal of Simulation, Systems, Science and Technology

JF - International Journal of Simulation, Systems, Science and Technology

IS - 1

M1 - 13

T2 - UKSim-AMSS

Y2 - 26 March 2024 through 28 March 2024

ER -

AI classification of respiratory illness through vocal biomarkers and a bespoke articulatory speech protocol

Abstract

Keywords

Access to Document

Fingerprint

Research output

Speech Breathing Under Cognitive Load: A Pilot Study of English and Arabic Bilingual Adaptation Using the Helicopter Test

Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders

Word or Phoneme? To Optimise Prosodic Features to Predict Lung Function with Helicopter Task

Exploring the Acoustic and Prosodic Features of a Lung Function Sensitive Repeated-word Speech Articulation Test

Activities

INTERSPEECH 2024

Helicopter task: exploring the acoustic, prosodic and breathing features of a lung function sensitive repeated-word speech articulation test

Speech Breathing Workshop

Cite this