Research
Five active projects spanning automatic transcription, real-time accompaniment, music–video generation, and embodied performance.
Fall 2024 – present
Automatic Music Transcription
Streamlining audio-to-MIDI transcription for musicians and educators, with applications in isolating sounds in noisy environments.
Learn more
Fall 2023 – present
Evaluator
An app that helps musicians practice more effectively, using computer vision and YOLO localization to track posture, with spectrogram analysis and multi-modal transformers to identify mistakes.
Learn more
Fall 2023 – present
Companion
An app that plays along with a human player during a chamber music piece and actively responds to their playing habits and voice commands.
Learn more
Spring 2022 – present
Mus2Vid
A real-time art project that uses diffusion models to generate video depictions in response to classical music, with recurrent and transformer networks estimating emotion and genre.
Learn more
Spring 2024 – present
Robot Cello
Using reinforcement learning to teach a robot arm to play cello. The project partners with the Purdue Envision Center for motion-capture training data.
Learn more