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

Artificial intelligenceCo-creative InterfacesPublicationsMachine Learning

May 24

Written By

This project has been archived!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

Report A Bug

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.)