Author: Boston University School of Medicine
Published: 2025/03/15
Publication Type: Simulation, Modelling
Peer-Reviewed: Yes
Topic: Biometrics - Publications List
Page Content: Synopsis - Introduction - Main - Insights, Updates
Synopsis: Researchers create pitch-shifting tools to protect privacy in voice-based cognitive assessments, maintaining diagnostic accuracy while safeguarding personal data.
Why it matters: Researchers at Boston University have developed innovative computational tools that use pitch-shifting and other audio transformations to protect the privacy of individuals in voice recordings without compromising the acoustic features necessary for assessing cognitive health. This is particularly useful as voice analysis offers a non-invasive method for detecting early signs of cognitive decline by examining speech patterns. The new framework addresses the significant privacy concerns associated with voice data, such as speaker identification, while still allowing for accurate differentiation between normal cognition, mild cognitive impairment, and dementia, as demonstrated in their study using data from the Framingham Heart Study and DementiaBank Delaware. This peer-reviewed work contributes to the ethical integration of voice data in medical analysis, offering a pathway to develop standardized, privacy-focused guidelines for future voice-based cognitive assessments that could benefit a wide range of people, including seniors and those with disabilities - Disabled World (DW).
Introduction
Obfuscation via pitch-shifting for balancing privacy and diagnostic utility in voice-based cognitive assessment.
Digital voice recordings contain valuable information that can indicate an individual's cognitive health, offering a non-invasive and efficient method for assessment. Research has demonstrated that digital voice measures can detect early signs of cognitive decline by analyzing features such as speech rate, articulation, pitch variation and pauses, which may signal cognitive impairment when deviating from normative patterns.
Main Item
Voice data introduces privacy challenges due to the personally identifiable information embedded in recordings, such as gender, accent and emotional state, as well as more subtle speech characteristics that can uniquely identify individuals. These risks are amplified when voice data is processed by automated systems, raising concerns about re-identification and potential misuse of data.
In a new study, researchers from Boston University Chobanian & Avedisian School of Medicine have introduced a computational framework that applies pitch-shifting, a sound recording technique that changes the pitch of a sound, either raising or lowering it, to protect speakers identity while preserving acoustic features essential for cognitive assessment.
"By leveraging techniques such as pitch-shifting as a means of voice obfuscation, we demonstrated the ability to mitigate privacy risks while preserving the diagnostic value of acoustic features," explained corresponding author Vijaya B. Kolachalama, PhD, FAHA, associate professor of medicine.
Using data from the Framingham Heart Study (FHS) and DementiaBank Delaware (DBD), the researchers applied pitch-shifting at different levels and incorporated additional transformations, such as time-scale modifications and noise addition, to alter vocal characteristics to responses to neuropsychological tests. They then assessed speaker obfuscation via equal error rate and diagnostic utility through the classification accuracy of machine learning models distinguishing cognitive states: normal cognition (NC), mild cognitive impairment (MCI) and dementia (DE).
Using obfuscated speech files, the computational framework was able to accurately determine NC, MCI and DE differentiation in 62% of the FHS dataset and 63% of the DBD dataset.
According to the researchers, this work contributes to the ethical and practical integration of voice data in medical analyses, emphasizing the importance of protecting patient privacy while maintaining the integrity of cognitive health assessments. "These findings pave the way for developing standardized, privacy-centric guidelines for future applications of voice-based assessments in clinical and research settings," adds Kolachalama, who also is an associate professor of computer science, affiliate faculty of Hariri Institute for Computing and a founding member of the Faculty of Computing & Data Sciences at Boston University.
About the Study Findings
These findings appear online in Alzheimer's & Dementia: The Journal of the Alzheimer's Association.
This project was supported by grants from the National Institute on Aging's Artificial Intelligence and Technology Collaboratories (P30-AG073104 and P30-AG073105), the American Heart Association (20SFRN35460031), Gates Ventures, and the National Institutes of Health (R01-HL159620, R01-AG062109, and R01-AG083735).
V.B.K. is a co-founder and equity holder of deepPath Inc. and CogniScreen, Inc. He also serves on the scientific advisory board of Altoida Inc. R.A. is a scientific advisor to Signant Health and NovoNordisk.
Editorial Note: The integration of privacy-preserving techniques like pitch-shifting into voice-based cognitive assessments signifies a pivotal step toward balancing technological advancement with ethical considerations. The ability to analyze voice data for early signs of cognitive decline represents a significant step forward in proactive healthcare. However, it's imperative that these advancements are deployed responsibly. This research underscores the importance of balancing technological innovation with ethical considerations, ensuring that the pursuit of better diagnostics does not come at the expense of individual privacy. As voice-based assessments become more prevalent, standardized, privacy-centric guidelines, as suggested by the researchers, will be essential for fostering trust and maximizing the benefits of this technology for all members of society. As we embrace digital health solutions, safeguarding personal information remains paramount, ensuring that innovations serve the public good without compromising individual privacy - Disabled World (DW).
Attribution/Source(s): This peer reviewed publication was selected for publishing by the editors of Disabled World (DW) due to its relevance to the disability community. Originally authored by Boston University School of Medicine and published on 2025/03/15, this content may have been edited for style, clarity, or brevity. For further details or clarifications, Boston University School of Medicine can be contacted at bu.edu NOTE: Disabled World does not provide any warranties or endorsements related to this article.
Citing and References
Founded in 2004, Disabled World (DW) is a leading resource on disabilities, assistive technologies, and accessibility, supporting the disability community. Learn more on our About Us page.
Cite This Page: Boston University School of Medicine. (2025, March 15). Voice Privacy Breakthrough: AI Safeguards Cognitive Tests. Disabled World (DW). Retrieved March 15, 2025 from www.disabled-world.com/assistivedevices/biometrics/voice-privacy.php
Permalink: Voice Privacy Breakthrough: AI Safeguards Cognitive Tests: Researchers create pitch-shifting tools to protect privacy in voice-based cognitive assessments, maintaining diagnostic accuracy while safeguarding personal data.
While we strive to provide accurate and up-to-date information, it's important to note that our content is for general informational purposes only. We always recommend consulting qualified healthcare professionals for personalized medical advice. Any 3rd party offering or advertising does not constitute an endorsement.