About
Imagine your signature, its particular loops with its particular rhythms.
Imagine writing your signature over and over until it becomes a loop and a beat.
Hold onto that sound.
Now imagine a machine that tries to guess your signature just from the sound.
With enough mics and training, would it, could it, reproduce your signature?

Our Vision

Our Technology
Deep Drawing is an intermedia AI co-performer that creates a real-time artistic dialogue with human artists on a shared web-based canvas.
Our system employs four contact microphones attached to a drawing surface to capture the subtle sounds of pen strokes.
Upon predicting the path of the pen through surface sound source localization, the system overlays its predictions onto a live video feed of the human drawing.
Publications
Deep Drawing: Spectra and Sound-Source Localization
The International Computer Music Conference (ICMC) 2025
Julie Zhu, Erfun Ackley, Zhiyu Zhang, John Granzow
Deep Drawing: An Intermedia AI Co-Performer
The International Conference on AI and Musical Creativity (AIMC) 2024
Julie Zhu, Erfun Ackley, Zhiyu Zhang, John Granzow
Our Team
Join Us
Deep Drawing is a UARTS FEAST (Faculty Engineering/Arts Student Teams) project sponsored by the ArtsEngine initiative at the University of Michigan. We are always looking for highly motivated students who are interested in the intersection of AI, music, and art.
Machine Learning
Signal processing and AI research roles
Summer Fellowships
Research fellowships for qualifying students
Open to All
All students on campus welcome