Our lab works at the intersection of music and machine learning. We focus on building a computational understanding of music and sound using state-of-the-art deep learning methods. Working across computational musicology, bioacoustics, emotion recognition, acoustic analysis, and non-speech audio understanding, we engage in deeply interdisciplinary, cutting-edge research in A.I. and data science.
This wiki serves as a living document for lab members to document technical processes, research workflows, model troubleshooting and other information which may be of use to the lab.
New lab members should start by reviewing the following pages to familiarize oneself with our lab's computational resources and experiment workflows
- Getting Started with the HPC
- Pytorch Hello World
- Using the Zotero
- MLOps with Neptune
- Using Jupyter on the HPC Portal (Pratik's To-Do)
- Music/digital audio basics (Derek to-do)