Steinberg has announced the immediate availability of Backbone 1.5, an update to their drum re-synthesizer, that lets you create original drum sounds using artificial intelligence and Neural Audio Synthesis.
Backbone 1.5 features DrumGAN, a recent development by Sony Computer Science Laboratories (Sony CSL), that uses Generative Adversarial Networks to generate original drum sounds. Available samples can also be analyzed to create similar versions.
A generative adversarial network (GAN) is a machine learning approach, in which two neural networks are used to improve the accuracy of artificially-generated output, with the goal of making the artificially-generated output indistinguishable from the source material that the model is trained on.
Well known examples of GANs can generate photorealistic portraits of people, cute cat pics and more.
“The cooperation between Sony CSL and Steinberg is a great example of how AI can be used in music production,” notes Steinberg’s Florian Haack. “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.”
Here’s a look at the technology behind DrumGAN:
Availability and Pricing
Backbone is available through the Steinberg Online Shop for 149 euros or 149.99 US dollars. With the release of version 1.5, Backbone is currently available at a 40% special offer discount until the end of July 2022. The update to version 1.5 is free for users who already purchased Backbone
how on earth did they manage to choose good drum sounds in the 80s without AI …must have been an impossible task, they must have been Geniuses….
uhmm, Kraftwerk!
They pretty much use AI in the wrong way to service music. Its as if the developers at Steinberg never tried to produce music at all. Pointless to have such a tool if its wrongly applied, this literately affects the effectiveness of workflow.
Why would you say is the wrong way or that it affects the efectiveness of workflow? This is basically like having all your drum sample library in a 200 Mb plugin. Would you say that exploring drum sample libraries is the wrong way of tackling beat production or that it affects the effectiveness of workflow?
The best thing about thispersondoesnotexist.com is that if you keep refreshing long enough you eventually come across people that only exist in your nightmares
the links in the article lead to “knockoff” versions of the original “…doesnotexist” sites
You can find less spammy links to the sites here: https://thisxdoesnotexist.com/
Thanks for the feedback – we updated the links in the post!
I know drummers you could get for the price of a pizza delivery tip.
AI? no thanks! Real Intelligence has presented bad enough results already.
Yeah, everybody can be a ‘composer’ in today’s music industry with those AI composing apps.
there needs to be more resythesis …. IMHO its one of the key technologies for methods of synthesis
it takes a ton of CPU horsepower, but these days that is widely available
im not sure about the AI part… but resynthesis as a technology is the next “big thing”…
might take a while though
I suppose one unforeseen value of AI generated drum samples could be to get things that are messed up– in ways you can’t do with distortions, etc. However, if they’ve made all the slider ranges fairly safe, then perhaps some of that glitchy behavior is prevented.
Is this instrument real or just generated? Another time-sucking solution looking for a problem. If someone is getting all anal about the purity of your kick sounds, they need a kick in the shorts.
IMO, fingers and drum sticks are the tools for this job. AI seems like a gimmick in this case.
Just in time! I was running out of drum sounds! 🙂
LOL
Between this and Spectralayers Steinberg is embracing some interesting technological apps. I’d like to see that from other companies as well.
This seems like a cool underlying technology, but I wish they pushed the envelope a little further. The kick, snare, and hi-hat sounds are all a bit basic sounding. It would have been far more interesting to let the user pick a set of parameters (ADSR, Tonal/atonal, timbre descriptors, etc) and then let a looser network generate some really weird possibilities.
I suspect we’ll see a lot more tools like this in the future, hopefully they are willing to get a little weirder than just recreating basic drum sounds.
you cant tweak details, just press random until u like the suggestion from ai
meh
im not impressed.
and for ppl that want ready made sounds you could just download a ton of samples and press next for the next “random” sample – takes the same amount of time to listen to that.
whats the point here?
also for cymbals a second is pretty short, they didnt even show it off – they know it sucks.
2030 Billboard charts: Dj AI, Dj Deep Learning…