Adobe is stepping into the realm of GenAI-powered music editing and creation with its unique take on the concept.
At the Hot Pod Summit in Brooklyn, the company introduced Project Music GenAI Control, a platform designed to generate audio from text descriptions or a reference melody, offering users the ability to customize the results seamlessly within the same workflow.
Key Features of Project Music GenAI Control
With Project Music GenAI Control, users gain control over various aspects of the generated music, such as tempo, intensity, repeating patterns, and structure. The platform empowers users to take a track and extend it to an arbitrary length, allowing for the creation of remixes, or even an endless loop.
This innovative tool promises to put users in the “director’s seat” of AI-generated music, providing a range of controls to explore and experiment with musical ideas without requiring extensive musical composition expertise.
Developed in collaboration with researchers from the University of California and Carnegie Mellon, Project Music GenAI Control is currently in the research stage, lacking a user interface. While Adobe has plans to make it publicly available in the future, the tool’s current focus is on exploring the possibilities of AI-generated music under user control.
Gautham Mysore, Adobe’s head of audio and video AI research, highlighted the collaborative nature of this tool, stating, “AI is generating music with you in the director’s seat, and there’s a bunch of things you can do with it.”
Legal Considerations in GenAI Music Tools
The rise of GenAI tools, including those for music creation, has brought about ethical and legal concerns. Instances of homemade tracks using GenAI to mimic authentic sounds, instruments, and vocals have gained attention. Music labels have responded with takedown requests, citing copyright concerns. The ethical question of whether “deepfake” music violates the intellectual property of artists, labels, and rights holders remains unanswered.
Mysore acknowledged these concerns and outlined Adobe’s responsible approach. The company trains its GenAI tools on data that is either under license or in the public domain, aiming to avoid potential intellectual property issues. While specifics about Project Music GenAI Control’s data usage remain undisclosed, Mysore emphasized that Adobe is actively working on watermarking technology to help identify audio produced by the platform. However, he acknowledged that this technology is a work in progress.
“Adobe takes a particularly responsible approach to [these things,]” Mysore added. “There’s a lot of really great musicians making this content … I think [they and tools like Project Music GenAI Control] are going to coexist. There’s going to be new musical ideas that come out.”
As Adobe ventures into the evolving landscape of AI-powered music creation, Project Music GenAI Control holds the potential to redefine how users interact with AI-generated musical compositions, ushering in a new era of creative possibilities.