There are plenty of music editing and creation tools powered by GenAI, but Adobe wants to put its own spin on the idea.
Today at the Hot Pod Summit in Brooklyn, Adobe unveiled Project Music GenAI Control, a platform that can generate sound from text descriptions (eg “happy dance”, “sad jazz”) or a reference melody and allows users to customize results in the same workflow.
Using Project Music GenAI Control, users can adjust things like tempo, volume, pattern repetition, and structure. Or they can take a track and extend it to an arbitrary length, mixing music or creating an endless loop.
Project Music GenAI Control, developed in collaboration with researchers at the University of California and Carnegie Mellon, may be made public at some future date. But for now, it’s firmly in the research stage, Adobe’s head of audio and video AI research Gautham Mysore said during a panel at Hot Pod — the platform doesn’t even have a UI yet.
“So the idea is that the AI creates music with you in the director’s seat, and there’s a lot of things you can do with it,” Mysore added. “[The tool is] produces music, but it is [also] giving you these different forms of control so you can try things out. You don’t have to be a composer, but you can get your musical ideas out there.”
GenAI music tools — and GenAI tools in general — are raising ethical and legal concerns as AI-generated music, artwork and text proliferate.
Home runs that use GenAI to create familiar sounds, lyrics and vocals that can pass as authentic, or at least close enough, have gone viral. Record companies were quick to do so request repeals, citing copyright. However, there is still a lack of clarity about whether “deepfake” music infringes on the IP of artists, labels and other rights holders — particularly in the case of GenAI music tools trained on copyrighted content.
Federal judge ruled in August that AI-generated art cannot be copyrighted. However, the US Copyright Office has yet to take an extremely firm stance, alone recently are beginning to seek public evidence on copyright issues as they relate to artificial intelligence. It’s also unclear whether users could be on the hook for violating copyright law if they try to commercialize music created in another artist’s style.
Mysore said that Adobe, as a general rule, develops its GenAI tools against data that is under license or in the public domain to avoid potentially offending IP issues. (It’s mum on whether that will happen with Project Music GenAI Control, though.) He added that Adobe is working on watermarking technology to help identify audio produced by Project Music GenAI Control, but admitted that it’s a work in progress.
“Adobe takes a very responsible approach [these things,]Mysore added. “There are a lot of really great musicians making this content… I think [they and tools like Project Music GenAI Control] they are going to coexist. There will be new musical ideas that will come out.”
