Machine Learning-Based Pitch and Chord Detection for Embedded Systems

This project proposal is to create an AI-based musical pitch and chord detection system suitable for deployment on a hardware device. Most of the research in this area is conducted on computer-based systems with large amounts of memory and computational power. Our goal is to develop new state of the art methods for doing this on embedded hardware, such as guitar pedals, keyboards, and more. Over an eight month period, the intern will work with Shift Audio to survey the current best methods for performing these tasks on computers and then modify and enhance them to make them suitable for embedded hardware. The intern will deliver a working prototype implementation of this system on development hardware that is suitable for quick integration into new systems. Shift Audio will benefit by generating new, unique technology that it can use in developing new products for its music technology clients.

Faculty Supervisor:

George Tzanetakis

Student:

Partner:

Shift Audio

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Victoria

Program: