Imitation System for Percussion
By: Jake Faris '15
Advising Faculty: Ozgur Izmirli
Jake built an imitation system for percussion which listens to a drummer and learns how to play standard rudiments through a process of listening to itself and correcting its mistakes. He worked on the project over a summer and the following two semesters. It was jointly presented with Professor Izmirli at the New Interfaces for Musical Expression conference held in London in July, 2014.
We present a framework for imitation of percussion performances with parameter-based learning for accurate reproduction. We constructed a robotic setup involving pull-solenoids attached to drum sticks which communicate with a computer through a microcontroller. The imitation framework allows for parameter adaptation to different mechanical constructions by learning the capabilities of the overall system being used. For the rhythmic vocabulary, we have considered regular stroke, flam and drag styles. A learning and calibration system was developed to perform grace notes for the drag rudiment as well as single strokes and the flam rudiment. A second pre-performance process was introduced to minimize the latency difference between individual drum sticks. We also developed an off-line onset detection method to recognize onsets from the microphone input. Once these pre-performance steps are taken, our setup will then listen to a human drummer’s performance, analyze for onsets, loudness, and rudiment pattern, and then play back using the learned parameters for the particular system. We conducted three different evaluations of our constructed system.
Related Fields: Computer Science