Nathan Fradet — accepted AI-conference papers

2025

MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition

Philippe Pasquier, Jeff Ens, Nathan Fradet, Paul Triana, Davide Rizzotti, Jean-Baptiste Rolland +1

AAAI 2025technical

We present and release MIDI-GPT, a generative system based on the Transformer architecture that is designed for computer-assisted music composition workflows. MIDI-GPT supports the infilling of musical material at the track and bar level, and can condition generation on attributes including: instrum…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Byte Pair Encoding for Symbolic Music

Nathan Fradet, Nicolas Gutowski, Fabien Chhel, Jean-Pierre Briot

EMNLP 2023long main

When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different approaches, as music can be composed of simultaneous tracks, o…

Cited by 0 Source ↗code ↗Scholar ↗