Apollo: An Interactive Environment for Generating Symbolic Musical Phrases using Corpus-based Style Imitation

This project has been archived!

Apollo is an interactive environment using corpus-based style imitation for symbolic music generation.
The user can generate symbolic music using their own metacreative algorithms and music corpora via a practical easy-to-use graphical user interface.
The system can interface with your favorite DAW (Digital Audio Workstation) such as Ableton Live via MIDI streaming.

See User Documentation

Apollo’s Application Workflow: Interactive Machine Learning (IML) for Music Creation

Demo

User scenarios

  • Generate style-imitation music to assist with your composition work

  • Find new creatively generated ideas for your next music project

  • Experience an alternative workflow to traditional music production

  • Explore AI possibilities in digital music composition

Features

  • MIDI corpora management: Enable constructing, saving corpus and selecting corpus

  • Music Generation of Musical Phrases: control model parameters for training and generation

  • Model Training: python AI model algorithms are packaged

  • MIDI playback (soundfonts) and streaming (e.g. to Ableton)

  • MIDI viewer/mixer and MIDI editor (incl. note editing)

  • Exporting features (download/upload)

  • Available online (Node.js server) or as a desktop app (Mac only)

  • VST (coming soon)

  • Install your own python AI algorithms

  • Ranking generated corpus against originals.

Curated music corpora

Available models: 5 symbolic models supported including Music Transformers.

Unique creative workflow (e.g. n-bar selections)


Research Papers

Bougueng R T and Ens J and Pasquier P. “Apollo: An Interactive Web Environment for Generating Symbolic Musical Phrases using Corpus-based Style Imitation”. In Proceedings of the 7th International Workshop on Musical Metacreation (MUME 2019). Vol. 7. June 2019.

Ens J, Pasquier P. “MMM: Exploring conditional multi-track music generation with the transformer”. arXiv preprint arXiv:2008.06048. 2020 Aug 13.

Ens J and Pasquier P. “Quantifying Musical Style: Ranking Symbolic Music based on Similarity to a Style”. In Proceedings of the International Symposium on Music Information Retrieval. Vol. 20. 2019, 870-877. (Oral Pres.)




Previous
Previous

Music Matters

Next
Next

ZETA