A person’s voice can express far more than just what they are saying. Researchers
are increasingly discovering that subtle changes in speech, breathing and vocal quality
provide valuable clues about a wide range of health conditions, from Parkinson’s and
Alzheimer’s to depression, heart failure and type 2 diabetes. These voice-derived
indicators, known as vocal biomarkers, are expected to soon be used for disease diagnosis
and monitoring.
To help unlock this potential, researchers and clinicians from the Department of Precision
Health (DoPH) at the Luxembourg Institute of Health (LIH) and the University of South Florida Morsani College of Medicine have led a new international effort to establish the
first consensus-based framework and definitions for vocal biomarkers.
Published in the journal Digital Biomarkers as part of the VOCAL (Vocal Biomarker Guidelines for Ontology, Classification, Application
and Logistics) initiative, the study brings together 24 international experts from
Europe and North America to address a key challenge facing voice-based health technologies:
the lack of a common scientific language.
As research on vocal biomarkers becomes more popular, the field’s rapid growth has
led to inconsistent terminology, with concepts such as “voice biomarkers,” “speech
biomarkers” and “vocal biomarkers” often used interchangeably, despite referring to
different physiological and cognitive processes.
To address this challenge, eVoiceNet — a European network coordinated by the Luxembourg Institute of Health, and Bridge2AI-Voice — a North American consortium funded by the NIH and co-led by USF researchers — conducted
a rigorous multi-stage consensus process between 2024 and 2025. The result is a structured
framework that clearly distinguishes between vocal measures and validated vocal biomarkers
and introduces a hierarchical model spanning the different domains involved in voice
and speech production.
The framework provides a scientifically grounded vocabulary designed to improve collaboration
between clinicians, speech and language specialists, engineers, data scientists, regulators
and industry stakeholders. It also aims to support the future development of standards,
validation pathways and regulatory guidance for voice-based health technologies.
“Voice has enormous potential as a source of health information, but the field cannot
progress efficiently without a common language,” said Dr. Guy Fagherazzi, head of
the Department of Precision Health at the LIH and chair of eVoiceNet. “By defining
what we mean when we talk about voice-based health measures, we are creating the foundations
for more robust research, greater transparency and, ultimately, clinically useful
technologies that can benefit patients.”
Dr. Yael Bensoussan, associate professor of Otolaryngology at the USF Health Morsani College of Medicine and co-head of the Bridge2AI-Voice consortium, said the framework reflects both the
promise and complexity of vocal biomarker research.
“One of the unique strengths of vocal biomarkers is that they capture information
from multiple physiological and cognitive systems simultaneously,” Bensoussan said.
“However, this complexity is also what has made the field difficult to define. This
work provides a structure that allows researchers to speak the same scientific language
while preserving the richness of the signal.”
The publication marks the first phase of the broader VOCAL initiative, which aims
to establish international guidelines and standards for vocal biomarker research and
implementation. The researchers hope that a shared vocabulary will help accelerate
the translation of voice-based technologies from the lab to the clinic.