MMM-Cubase

Audio & MusicCo-creative InterfacesSystems
Written By Griffin Page

MMM-Cubase workflow

The Cubase-MMM system is a plugin for the Cubase digital audio workstation (DAW) that provides computer-assisted composition (CAC) functions based on the Multi-track Music Machine (MMM), a generative pre-trained transformer (GPT) model. MMM-C offers users a set of parameters to guide music generation within their composition workflow, including:

  • Global parameters: These parameters define high-level aspects of the generated musical content, such as:

  • Musical genre (e.g. Pop, House, Electronic, Jazz)

  • Musical pattern (e.g., Automatic, Polyphonic, Monophonic, Drum)

Advanced parameters: These parameters provide more fine-grained control of MMM's generative behavior, including:

  • Duration (e.g., Whole, 1/2, 1/4, 1/8, 1/16, 1/32)

  • Density (e.g., Automatic, Low, Medium, High)

  • Repetition (e.g., Automatic, Low, Medium, High)

  • Craziness (0-100%, default 50%)

  • Replace Selection vs. Add to Selection

The user workflow for MMM-C v2 typically involves:

  • Selecting bars of symbolic music content on an existing or new track in the Cubase piano roll interface.

  • Adjusting the global and advanced parameters to refine the intended generated output.

  • Triggering the generation process by clicking the "Generate" button.

MMM-C then generates the new musical sequences directly into the selected bars of the piano roll. The system also features a "Cancel" button to interrupt generation, and leverages Cubase's undo-redo functionality to revert generative edits.

The latest version of MMM-Cubase is using the MIDI-GPT model.

MMM-Cubase is currently available for research and demonstrative purposes. It is not available publicly or commercially. Contact us for more information.

MMM-Cubase has been evaluated for user-friendliness in the following studies:

Tchemeube, Renaud Bougueng and Ens, Jeffrey and Plut, Cale and Pasquier, Philippe and Safi, Maryam and Grabit, Yvan and Rolland, Jean-Baptiste. Evaluating Human-AI Interaction via Usability, User Experience and Acceptance Measures for MMM-C: A Creative AI System for Music Composition. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 5769-5778, 2023

Forthcoming: Evaluating Human-AI Interaction in Computer-Assisted Music Composition with MMM-Cubase v2

Griffin Page
Previous

Music with MMM
Next

Revival