Logo Sony

Steinberg’s Backbone 1.5 incorporates Sony CSL’s DrumGAN

Steinberg has today announced the immediate availability of Backbone 1.5, the latest version of the company’s drum re-synthesizer. This updated iteration includes a new key feature, DrumGAN, a recent development by Sony CSL which employs AI-driven technology to generate unique drum samples.

Drum design plays a prominent role in arranging and producing a song. While professionally-recorded sound libraries are available for editing, browsing sample packs or fiddling with expert controls in a sampler can be a barrier to creativity for some people.

 

DrumGAN is a technology researched and developed by the members of the music team in Sony CSL Paris to generate unique drum sounds using AI. Instead of relying on existing audio samples, DrumGAN allows creators to effortlessly synthesize original drum sounds from scratch by adjusting smart parameters, such as “kick-ness”, “snare-ness”, and “cymbal-ness”.

06
After a few months of experimenting with DrumGAN, Twenty9 releases his Drumkit made out of AI-generated sounds

DrumGAN’s core technology is Neural Audio Synthesis, a new audio generation technology based on neural networks. Neural networks are widely used in the field of imagery, such as in generating realistic-looking pictures of human faces but they can also be applied to audio. In 2020, Sony Music Publishing-affiliated music producer Twenty9 released the world’s first AI-powered drum kit using DrumGAN. 

 

With its incorporation in Steinberg’s Backbone, DrumGAN will be the world’s first commercially available technology to employ Neural Audio Synthesis. Today, thanks to the Sony CSL-Steinberg partnership, DrumGAN is more user-friendly as a tool and is available to creators around the world. Sony CSL will continue accelerating its research and practical application of AI technology empowering music creators to enhance their creativity.

Steinberg’s Backbone is a virtual instrument which provides new ways to design primarily intricate drum sounds for every style of music. Users start off by layering up to eight samples, which can be split into individual tonal or noise elements. The individual layers can also be resynthesized with easily accessible manipulation tools through the clearly laid out user interface.

 

By adding DrumGAN, Backbone 1.5 is now taken to a new level of individuality for creating sounds. DrumGAN uses Generative Adversarial Networks to generate new drum sounds with only a few smart parameters. Available samples can also be analyzed to create similar versions. With this latest AI-driven technology, Backbone users now have options to take their sounds into previously uncharted territory, creating a wide range of signature sounds that have literally never been heard before

 

Senior Marketing Manager Florian Haack says: “The cooperation between Sony CSL and Steinberg is a great example of how AI can be used in music production to drive creativity while making everything easier. The ability to generate new samples with DrumGAN for kicks, snare or cymbals, or analyze existing samples and further re-synthesize and reassemble the components gives producers unprecedented flexibility to design new sounds. And, thanks to the user-friendly interface, Backbone users can now harness this new AI-powered technology in a straightforward way.”