EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Obfuscation via pitch‐shifting for balancing privacy and diagnostic utility in voice‐based cognitive assessment

Meysam Ahangaran, Nauman Dawalatabad, Cody Karjadi, James Glass, Rhoda Au, Vijaya B Kolachalama iD

Alzheimer's & Dementia · 2025

DOI: 10.1002/alz.70032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Alzheimer's & Dementia, 2025. Verfasst von Meysam Ahangaran und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, Boston University Chobanian and Avedisian School of Medicine, Boston, Massachusetts, USA. Hauptthemen laut MEDLINE: Cognitive Dysfunction, Neuropsychological Tests, Voice, Dementia. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Institute on Aging's Artificial Intelligence and Technology Collaboratories, Gates Ventures, American Heart Association.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION Digital voice analysis is an emerging tool for differentiating cognitive states, but it poses privacy risks as automated systems may inadvertently identify speakers. METHODS We developed a computational framework to evaluate the trade‐off between voice obfuscation and cognitive assessment accuracy, using pitch‐shifting as a representative method. This framework was applied to voice recordings from the Framingham Heart Study (FHS, n = 128) and the DementiaBank Delaware (DBD, n = 85) corpus, both featuring responses to neuropsychological tests. Speaker obfuscation was measured via equal error rate (EER), and diagnostic utility was assessed through machine learning models distinguishing cognitive states: normal cognition (NC), mild cognitive impairment (MCI), and dementia (DE). RESULTS With the top 20 acoustic features, our framework achieved classification accuracies of 62.2% (EER: 0.3335) on the FHS dataset for NC, MCI, and DE differentiation, and 63.7% (EER: 0.1796) on the DBD dataset for NC and MCI differentiation, using obfuscated speech files. DISCUSSION Our results demonstrate the feasibility of privacy‐preserving voice markers, offering a scalable solution for voice‐based cognitive assessments. Highlights We developed a computational framework using pitch‐shifting and acoustic transformations to balance speaker privacy and diagnostic utility in voice‐based cognitive assessments. We evaluated the framework on two independent datasets, Framingham Heart Study (FHS, n = 128) and DementiaBank Delaware (DBD, n = 85) corpus, assessing the trade‐off between privacy (measured by equal error rate [EER]) and classification accuracy. Our framework achieved classification accuracies of 62.2% (EER: 0.3335) for distinguishing normal cognition (NC), mild cognitive impairment (MCI), and dementia in the FHS dataset and 63.7% (EER: 0.1796) for NC and MCI differentiation in the DBD dataset, using obfuscated speech files. Our framework demonstrates that pitch‐shifting levels can preserve diagnostic utility while protecting speaker identity, offering a scalable and privacy‐preserving solution.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cognitive DysfunctionNeuropsychological TestsVoiceDementiaPrivacyHumansMaleFemaleAgedCognitionMachine Learning

Stichwörter der Autor:innen

cognitive assessmentdigital healthprivacyvoice recordings

Autor:innen und Institutionen

  • Department of Medicine, Boston University Chobanian and Avedisian School of Medicine, Boston, Massachusetts, USA.
  • Zoom Communications Inc., San Jose, California, USA.
  • Department of Anatomy and Neurobiology, Boston University Chobanian and Avedisian School of Medicine, Boston, Massachusetts, USA.
  • The Framingham Heart Study, Boston University Chobanian and Avedisian School of Medicine, Boston, Massachusetts, USA.
  • Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
  • Department of Neurology, Boston University Chobanian and Avedisian School of Medicine, Boston, Massachusetts, USA.

ORCID-Profile: Vijaya B Kolachalama

Förderung

  • National Institute on Aging's Artificial Intelligence and Technology Collaboratories
  • Gates Ventures
  • American Heart Association
  • NIH HHS
  • NHLBI NIH HHS
  • NIA NIH HHS
  • National Institutes of Health

Zitieren

APA

Ahangaran, M., Dawalatabad, N., Karjadi, C., Glass, J., Au, R., & Kolachalama, V. B. (2025). Obfuscation via pitch‐shifting for balancing privacy and diagnostic utility in voice‐based cognitive assessment. Alzheimer's & Dementia. https://doi.org/10.1002/alz.70032

Vancouver

Ahangaran M, Dawalatabad N, Karjadi C, Glass J, Au R, Kolachalama VB. Obfuscation via pitch‐shifting for balancing privacy and diagnostic utility in voice‐based cognitive assessment. Alzheimer's & Dementia. 2025. doi:10.1002/alz.70032

BibTeX
@article{Ahangaran2025,
  author = {Ahangaran, Meysam and Dawalatabad, Nauman and Karjadi, Cody and Glass, James and Au, Rhoda and Kolachalama, Vijaya B},
  title = {Obfuscation via pitch‐shifting for balancing privacy and diagnostic utility in voice‐based cognitive assessment},
  journal = {Alzheimer's & Dementia},
  year = {2025},
  doi = {10.1002/alz.70032}
}
Kostenlos starten →