By Donna Smith, University Marketing and Communications
Recent developments in artificial intelligence are empowering researchers to evaluate how one's voice can assist in the prediction and early detection of disease. In collaboration with the USF AI+X Institute, USF Health is helping train the next generation of medical professionals through the launch of its first-ever course dedicated to understanding how voice can be used as a biomarker for health - helping to identify neurological, respiratory and psychiatric diseases.
Dr. Yael Bensoussan
"While there are many programs that teach students how to work with imaging and other clinical data, being prepared to understand and analyze voice data is going to put these students in a unique position," said laryngologist Dr. Yael Bensoussan, assistant professor of otolaryngology at USF Health. "There are many startups out there in many different industries that are looking for that expertise, because it's still really rare to find it. We're positioning them to be to be ready to go apply for these jobs."Bensoussan is co-principal investigator of the National Institutes of Health-funded Bridge2AI-Voice program, a consortium of 50 professionals such as clinicians, speech pathologists, informaticians, AI scientists and bioethicists working to standardize AI datasets and their ethical use in health care.
As part of the program, USF is one of four universities nationwide selected to host the inaugural Voice AI Summer School. The five-week course is training students ranging from undergraduates to medical students to process voice audio, identify acoustic and speech features, such as hoarseness or tremor, and train and test algorithms that can screen and or aid in diagnosis.
Trevor Pharr
Trevor Pharr, a rising second-year student in the USF Health Morsani College of Medicine, says that his love for singing led to an interest in becoming a physician specializing in otolaryngology. Pharr completed a double major in biochemistry and music at the University of North Carolina, Chapel Hill, and is now studying the groundbreaking field of voice AI.
"I would never have guessed I'd be studying this, but it's a bit serendipitous that this really, really good voice study is happening now, because it is something I've been interested in for years," Pharr said. "I'm just glad to be a part of this experience."
Forty-five students from across the country were selected for the intensive program, with 15 based at USF. They're divided into teams made up of students from the tech and the health fields. Students practice how to collect voice data and are invited to volunteer their own voices, which Bensoussan says further deepens their understanding of the technology.
"Sometimes engineers are presented with data without necessarily understanding how it was collected," Bensoussan said. "I think it's really important to understand how it was collected, and the best way to understand it is to do it yourself."
Faculty members from USF's AI+X Institute - a multidisciplinary research and development center focused on AI - are teaching sessions on the intricacies of AI model development using acoustic data for health care purposes. Many are from the USF Department of Computer Science and Engineering, including Distinguished University Professor and Chair Sudeep Sarkar. He's also associate vice president for Research & Innovation at USF and serves as a director at the AI+X Institute.
"Our involvement underscores our commitment to fostering the next generation of AI researchers and practitioners from different disciplines - the '+X' part of our identity," Sarkar said. "This program provides a unique platform for participants to gain hands-on experience, engage with cutting-edge research and collaborate with leading experts in the unique problem domain of voice-based medical diagnosis."
Shriamana Ganesh-Sudhadhakai
Shriamana Ganesh-Sudhadhakai is a second-year master's student at Georgia Tech University studying bioinformatics. He is attending the Voice AI Summer School because he hopes to enter the bioinformatics workforce.
"Bioinformatics falls somewhere in between biology and computer science," Ganesh-Sudhadhakai said. "I want to be in the industry focusing on research and product development, so the ideal goal for me is to learn all the technology that is available right now."
Bensoussan hopes that the benefits of the Voice AI Summer School will have a far reach beyond just the students who are enrolled.
"A lot of our project is open science, so hopefully the curriculum we're building will be able to benefit a broader community, because that's how things are discovered."
