Logo acustica 2017

Introducing Cola

Acustica's first AI Deep-Learning powered plugin.

 

COLA AI: SAMPLING GEAR. AND HUMANS.

With Cola, we have introduced a first-of-its-kind in AI-based approaches to mixing. Unlike other companies, who classify audio content (violins, drums, vocals, etc.) with the aim of implementing an auto-mix functionality with the software, we have chosen a completely different approach.

We are not new to Artificial Intelligence technology. In fact, we have been using 'AI-based machine learning' while developing our compressors.

But Deep Learning techniques - applied to our already unique hardware sampling technology - will be a true game changer as - to our knowledge - the creative approach of an engineer to mixing has never been 'sampled' and recreated in a plugin.

TAKING A.I. TO THE NEXT LEVEL WITH DEEP LEARNING.

Deep Learning takes the principles of AI and elevates them, for results and new perspectives never explored before in the audio plugin world.

Starting from a psychoacoustic and spectral analysis of the material, this approach allows us to actually 'sample' the engineer's own approach to working on a specific track - or a full mix - so that his or her approach can be creatively replicated in different situations.

SO, HOW DOES IT WORK?

Long story short, the engineer we intend to 'sample' is given a prototype version of the plugin, which she/he uses for a certain period of time on various sources, tracks and full mixes, just like any regular plugin. But under the hood, the plugin writes data based on the choices of the engineer and learns to repeat these choices. After this stage, this data is put together so that the plugin remembers what to do and when to do it.

We can literally 'teach' the plugin the pro's 'secret moves' so they can be easily replicated and can work as starting points for other engineers or musicians seeking a particular sound.

How would this engineer treat this track? What kind of compression would she/he use? How can I treat this instrument to make it sit in the mix properly?

With AI and Deep Learning we intend to answer these and many other questions, because we are not just creating presets, we are recreating a pro's unique touch based on the audio material.

CREATIVE FREEDOM. THE IRIS™ PROJECT.

As complicated and 'nerdy' as this might seem, this is actually all about the style and unique creative approach of every great engineer and not just about creating fixed 'presets'.

 As pioneers of this new approach, we admit that there is still a lot of work necessary to fully unleash the potential of such technology, but we can say that the first results are very promising indeed. The IRIS™ Project has just begun!

Cookies help us deliver our services. By using our services, you agree to our use of cookies. Learn more