​Music Data Preprocessing Pipelines

​Presenter: Dr. Alexander Sigman – Engineer and musician based in Luxembourg, with 6+ years of experience working at generative music AI startups. Prior to (and even after) transitioning into industry, he was active in academia in the US, Korea, and Japan. His music has been commercially released on the New Focus, Carrier, and Innova labels.

​What to Expect: Data pipeline construction is a crucial but often undervalued stage in the music ML model training process. In this hands-on tutorial, you will gain experience in (audio) data and (text) metadata preprocessing, validation, and storage, as well as handling music-specific Dataset classes and dataloaders in Pytorch. Music representation strategies (waveforms, spectrograms, embeddings, etc.) and tradeoffs thereof will also be addressed. Although prior experience in Pytorch would be helpful, basic knowedge of Python and of audio/DSP concepts would suffice for the purposes of this session.

​How to join:

• ​This session is public and will be live-streamed on our Discord channel: Sign-up to get the link.

​Future Sesssions:

• ​If you are not a member, join Munich Music Labs to get full access to our knowledge-sharing sessions:

  • ​MML Member Sign-Up Form

• ​Subscribe to our Luma calendar to stay up to date with upcoming events!

  • ​MML Luma calendar