PhD graduated
Team : SMA
Departure date : 03/31/2024


Co-supervision : BRIOT Jean-Pierre

Deep Learning for Symbolic Music Modeling

Symbolic music modeling (SMM) represents the tasks performed by Deep Learning models on the symbolic music modality, among which are music generation or music information retrieval. SMM is often handled with sequential models that process data as sequences of discrete elements called tokens. This thesis studies how symbolic music can be tokenized, and what are the impacts of the different ways to do it impact models performances and efficiency. Current challenges include the lack of software to perform this step, poor model efficiency and inexpressive tokens. We address these challenges by:

  1. developing a complete, flexible and easy to use software library allowing to tokenize symbolic music;
  2. analyzing the impact of various tokenization strategies on model performances;
  3. increasing the performance and efficiency of models by leveraging large music vocabularies with the use of byte pair encoding;
  4. building one of the first large-scale model for symbolic music generation.

Defence : 03/14/2024

Jury members :

Jean-Pierre Briot - LIP6, Sorbonne Université/CNRS
Amal El Fallah Seghrouchni - LIP6, Sorbonne Université/CNRS
Nicolas Gutowski - LERIA, Université d'Angers
Fabien Chhel - ESEO, ERIS
Louis Bigo - LaBRI, Université de Bordeaux/CNRS
Philippe Pasquier - Simon Fraser University
François Pachet - Spotify
Gaëtan Hadjeres - Sony AI

Departure date : 03/31/2024

2021-2024 Publications

  • 2024
  • 2023
  • 2021
    • N. Fradet, J.‑P. Briot, F. Chhel, A. El Fallah‑Seghrouchni, N. Gutowski : “MidiTok: A Python Package for MIDI File Tokenization”, Extended Abstracts for the Late-Breaking Demo Session of the 22nd International Society for Music Information Retrieval Conference, Online, United States (2021)