Knowledge Sharing | Recent Developments in Generative Music AI Models: Capabilities and Limitations
We're excited to announce our first public Knowledge Sharing Session!
Recent Developments in Generative Music AI Models: Capabilities and Limitations
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: Over the past several years, a few dominant state-of-the-art architectures have emerged in the realm of generative music AI, in both the audio and symbolic domains. However, a clear understanding of the mechanics of these models is often inhibited by media hype and perplexing terminology. In this presentation, Dr. Sigman will outline the intuitions behind and salient features of autoregressive, diffusion, flow matching, and related model types, as well as their respective strengths, weaknesses, and music-specific use cases. To provide a broader context for the adoption of these resource-intensive architectures, the performance limitations of older machine learning and symbolic algorithms will be addressed.
How to join:
This session is public and will be live-streamed on our Discord channel: Sign-up to get the link.
Everybody is welcome to join and learn from an expert in the field of Generative Audio AI.
Future Sesssions:
If you are not a member, join Munich Music Labs to get full access to our knowledge-sharing sessions:
Subscribe to our Luma calendar to stay up to date with upcoming events!