Skip to content

Repository files navigation

CMU 15-798 F25: Generative AI for Music and Audio

Quick links

Important information

  • Class sessions: MW 12:30-1:50P, GHC 4101
  • Instructor: Chris Donahue
    • Office hours: W 2-3P (right after class), GHC 7127, or by appointment
  • TA: Irmak Bukey
    • Office hours: TBD
    • Office location: TBD

Description

This is a graduate level course on generative AI taught through the lens of music and audio taught by Chris Donahue. We aim to study this topic holistically, covering everything from the core ML methods behind state-of-the-art music AI systems such as Suno, to principles of interaction with music AI systems, to the broader societal implications of music AI.

Methods for generative AI are increasingly consolidating across modalities. Our focus here will be on the domain-specific application of generative AI to music and audio, though many of the skills you learn will transfer to other modalities such as speech, images, video, or even text. A key focus will also be on writing and oral communication skills in research, which will transfer to any other research pursuit.

Major course activities will center around:

  1. Reading and discussing research papers
  2. Completing programming assignments in Google Colab / Python / PyTorch
  3. Conducting an original research project and writing a paper

Before enrolling, please see the Syllabus and Activities for more details.

About

Course information for CMU 15-798 F25: Generative AI for Music and Audio

Resources

Stars

6 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages