Loading…

Loading grant details…

Active STANDARD GRANT National Science Foundation (US)

I-Corps: Translation Potential of Driven Voice Biomarkers for Medical Devices and Applications

$500K USD

Funder National Science Foundation (US)
Recipient Organization University of Maryland, College Park
Country United States
Start Date May 15, 2025
End Date Apr 30, 2026
Duration 350 days
Number of Grantees 1
Roles Principal Investigator
Data Source National Science Foundation (US)
Grant ID 2529908
Grant Description

This I-Corps project focuses on the development of a software-based tool that enables health-focused applications and medical devices to detect health-related features in a person's voice. This tool aims to solve a widespread problem in healthcare: the lack of accessible, non-invasive, and continuous methods for monitoring chronic and emerging health conditions.

By analyzing speech for vocal patterns linked to conditions such as neurological disorders, respiratory diseases, and mental health concerns, this tool supports early detection and personalized treatment. The ability to monitor these conditions using only voice recordings has broad implications for improving patient outcomes, reducing healthcare costs, and extending high-quality care to in-person and remote communities.

This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on an application programming interface that enables medical systems to extract and analyze voice biomarkers from speech audio using advanced signal processing and machine learning techniques.

The tool identifies features derived from articulatory dynamics and acoustic characteristics of the voice that correlate with various health, wellness, and medical states. The solution incorporates near real-time, cloud-enabled processing and uses state-of-the-art models to analyze subtle vocal changes, including deep learning frameworks that go beyond traditional spectral features.

This technology enables seamless integration into healthcare systems, offering high sensitivity in detecting early signs of health problems and / or deterioration over time. The solution is designed to be efficient, scalable, and adaptable across a wide range of healthcare applications, offering care providers, clinicians, and developers a new, data-driven tool for enhancing diagnostic and monitoring capabilities.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

All Grantees

University of Maryland, College Park

Advertisement
Discover thousands of grant opportunities
Advertisement
Browse Grants on GrantFunds
Interested in applying for this grant?

Complete our application form to express your interest and we'll guide you through the process.

Apply for This Grant