Machine learning comes to Ableton Live with Factorsynth, a Max For Live device that uses a data analysis algorithm called matrix factorization to decompose any audio clip into a set of temporal and spectral elements. By rearranging and modifying these components you can do powerful transformations to your clips, such as removing notes or motifs, creating new ones, randomizing melodies or timbres, changing rhythmic patterns, remixing loops in real time, applying effects selectively only to certain elements of the sound, creating complex sound textures...
After 2 years of the initial release comes Factorsynth 2, the first major update. Following many user suggestions and requests, version 2 is an even more versatile yet easier to use device, with a simplified workflow and numerous new features. It is now possible to individually pan the components, allowing to do things such as upmixing a mono clip to stereo. Another powerful new feature is the quantized shifting of the components, which allows changing the rhythmic structure of riffs and drum loops. A second, alternative decomposition algorithm is available, as well as a more detailed control of the playback region.
 Quite magical. - The Pro Audio Files | Get truly new types of sounds with this amazing device! - Seed to Stage |
| A powerful instrument for breaking down audio loops in to timbral and spectral elements that can be remixed and exported in astoundingly cool ways. - Ask.Audio | From intelligent remixing to sound textures and spectral composition, it will appeal to many composers, musicians and sound designers. - KR Home Studio |
EDITIONS
There are two editions of Factorsynth: the full edition (whose current version is Factorsynth 2) and a lightweight edition called FACTORmini. Both are based on the same decomposition engine, but the full version has a wider range of synthesis operations. This table compares both versions' main features:
| 
| |
| Maximum components | 8 | 30 |
| Factorsynth decomposition engine | 
|
|
| Export components |
|
|
| Cross-synthesis | 
|
|
| Detailed component editing |
|
|
| Component panning |
|
|
| Component shifting |
|
|
| Price (excl. VAT) | 29 € | 49 € |
BUY
|
| SYSTEM REQUIREMENTS
CURRENT VERSION v2.0, 10/7/2020 |
| 49 € + V.A.T. Buy | |
| Terms and conditions | |
Upgrade offersUpgrade to Factorsynth 2 is free for current users of Factorsynth (v. 1.5 and older). Also, users of Factormini can upgrade to Factorsynth 2 at a discounted price of 25 Euros plus taxes. If you have purchased one of the devices and didn't get an email with a discount code, please contact software@jjburred.com.
| IRCAM ForumFactorsynth is a partner product of the IRCAM Forum. Premium members of the forum can get special discounts. For further details, please consult Factorsynth's IRCAM forum page.
|
DOCUMENTATION
FACTORSYNTH USER MANUAL: 
FACTORSYNTH CHANGE LOG: CHANGELOG.txt
For any usage or support related questions, please contact software@jjburred.com.
You can also sign up to the mailing list: 
Here's a recent article I wrote about Factorsynth's place in the Machine Learning landscape.
If you're interested in learning some more details about the technology behind Factorsynth, you can check these research papers:
- Factorsynth: a Max tool for sound analysis and resynthesis based on matrix factorization, Proc. SMC, August 2016.
- A Framework for Music Analysis/Resynthesis Based on Matrix Factorization, Proc. ICMC, September 2014.
- Cross-Synthesis Based on Spectrogram Factorization, Proc. ICMC, August 2013.
FAQ
How do Factormini and Factorsynth work?
Factormini and Factorsynth are based on a modified version of an algorithm called Non-Negative Matrix Factorization
(NMF). Simply put, NMF can automatically extract interesting patterns
from data. It has been used in fields such as computer vision and movie recommendations. I had to heavily adapt and tweak it in order to meet
the real-time needs of music production.
Can Factormini or Factorsynth remove a full voice/instrument from a mix?
That's unlikely, unless your voice or instrument plays only a few sustained notes, with no effects and no vibrato. Factormini and Factorsynth can extract interesting
sound events, such as individual notes, attack noises, impulses or rhythmical structures (watch the demo video to get an idea), but it's not aimed at separating full instruments. That's the
job of source separation, which is a harder thing to do! On the other hand, you can often nicely separate drum sets and individual drum instruments (kick drums,
hi-hats, snares...). For more details about this, check out this blog post.
Can Factormini's or Factorsynth's parameters be controlled by Live's automation envelopes or MIDI mappings?
Most of them can (factorization buttons, matrix operation buttons, solo buttons, number of components, all levels and pan sliders,
shifting buttons, transport controls and quantization). Also, the first 8x8 buttons
on the switchboards are MIDI-assignable. The ones that cannot be controlled by Live are: analysis parameters, clear panel, export panel, “snap" and “all" buttons on the output waveform display, reset and threshold buttons and individual
buttons on the switchboards corresponding to component numbers higher than 8.
Can Factormini and Factorsynth be used with standalone Max?
Yes, starting from version 1.5 it is possible to use them with the standalone Max application, without Ableton Live. There is a bit of patching needed to set it up.
For details, you can take a look at the "Usage from Max" section in the manuals.