Computer Vision and Audio Can Analyze Playing When Instructors Are Scarce
Sometimes students need an instructional pick-me-up between violin lessons. Others can’t afford as many lessons as their talent merits, or they live in a place where violin teachers are in short supply.
A new artificial intelligence-powered system under development by a University of Maryland classical violinist and a computer scientist with expertise in robotics and computer vision could fill in those gaps.
“Our project combines the expertise of traditional violin pedagogy with artificial intelligence and machine learning technology,” said Irina Muresanu, an internationally known concert violinist and an associate professor of violin in the School of Music. “Our aim is to ultimately create software that will be able to provide guidance for all string instruments, and even other instruments.”
The system is not designed to replace human expertise, but to augment it, the researchers say.
“Our system will observe the players using vision and audio, and will analyze the playing in order to give the appropriate feedback, and also to give suggestions on what to practice,” said Cornelia Fermüller, a research scientist with the Institute for Advanced Computer Studies and the Computer Vision Laboratory.
The research is funded by a 2021 Maryland Innovation Initiative Award, as well as a Grand Challenges Team Project grant announced last week.
Maryland Today is produced by the Office of Marketing and Communications for the University of Maryland community on weekdays during the academic year, except for university holidays.
Faculty, staff and students receive the daily Maryland Today e-newsletter. To be added to the subscription list, sign up here:Subscribe