Cornelia Fermuller
University of Maryland, MD·Computer Science
Learning a skill like playing the violin means linking how you move with what you hear, and expert one-on-one teaching is costly and scarce. Two of these projects use computer vision and audio analysis to build an artificial intelligence (AI) violin tutor.
- Fields
Computer Science
Engineering
Education Research
- Topics
artificial intelligence
computer vision
audio analysis
- Grants
- 3 known grants, through Aug 2027
What they work on
- Develop machine-learning methods that analyze video and audio of violin students to judge posture, bowing and sound quality, and explain causally why a movement error produced a poor sound.
- Build a system that assigns personalized practice material from a recorded and categorized corpus of violin teaching pieces, based on automated evaluation of each student's playing.
- Assess the market potential of a webcam-and-microphone AI violin tutor through I-Corps customer discovery with schools, music teachers and students.
- Coordinate an international network advancing neuromorphic models of sensorimotor control, motor learning and spiking neural networks, applied to drone navigation and humanoid robots.
More about the research
A third links an international network studying neuromorphic systems, which are low-power computing systems modeled on the brain that tie perception to action.
Why it matters
An affordable AI violin tutor that needs only a webcam and microphone could bring instrument instruction to students who cannot afford private lessons. It could also help them avoid injury-prone technique and give teachers insight into practice habits. Brain-inspired, low-power computing could eventually enable applications such as on-phone computing, neuroprostheses, intelligent hearing aids and smart sensors.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Emphasizing Explanation in AI Augmented String Instrumental Education
NSF · Sep 2023 – Aug 2027
AccelNet: Accelerating Research on Neuromorphic Perception, Action, and Cognition
NSF · Jan 2021 – Mar 2027
I-Corps: Translation potential of an artificial intelligence-based violin tutoring system
NSF · Jan 2025 – Sep 2026
Closest labs
Sarah Hansen
Columbia University, NY·Education Research
Compare webcam-based eye tracking with traditional screen-based eye tracking while students solve chemistry problems. Determine whether low-cost webcams capture viewing behavior well enough for research and feedback.
Sergei Nirenburg
Rensselaer Polytechnic Institute, NY·Computer Science
Assess the commercial translation potential of a cognitive-robotics technology through experiential learning and first-hand investigation of the industry ecosystem.
Tahir Ekin
Texas State University, TX·Computer Science
Develop an Applied AI Summer School and new course modules in data analytics, Python, deep learning, natural language processing and computer vision for students in non-AI disciplines, using inclusive and contextualized teaching methods.
The school
University of Maryland: 49 labs on PI Pages, $1.5B a year on research, 602 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.