Musician-Centered music AI: Generation, Separation, Interpretation and Performance

​Tornike is an audio Machine Learning researcher with a Ph.D. in computer music from UC San Diego. He focuses on deep neural sound synthesis, computational creativity, and spatial audio, using diffusion, transformers, VAEs, and GANs to generate high-quality audio from text and other inputs.

​In this presentation, Tornike will highlight the challenges of the dominant text-to-music paradigm. For generative models to be truly useful to musicians, they need to maintain a process where music production is creative, iterative, progressive, and multi-modal. This process requires orchestrating individual parts, analyzing texture, interpreting notation, and interacting in real time.

​How to join:

• ​This session is public and will be live-streamed: 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