FRADET Nathan
Forschungsgruppe : SMA
Datum, an dem das LIP6 verlassen wurde : 31.03.2024
https://nathanfradet.com
Forschungsleitung (Direction de recherche) : Amal EL FALLAH SEGHROUCHNI
Co-Betreuung : 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:
- developing a complete, flexible and easy to use software library allowing to tokenize symbolic music;
- analyzing the impact of various tokenization strategies on model performances;
- increasing the performance and efficiency of models by leveraging large music vocabularies with the use of byte pair encoding;
- building one of the first large-scale model for symbolic music generation.
Verteidigung einer Doktorarbeit : 14.03.2024
Mitglieder der Prüfungskommission :
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
Publikationen 2021-2024
-
2024
- N. Fradet : “Deep Learning for Symbolic Music Modeling”, these, verteidigung einer doktorarbeit 14.03.2024, forschungsleitung (direction de recherche) El fallah seghrouchni, Amal, co-betreuung : Briot, Jean-Pierre (2024)
-
2023
- N. Fradet, N. Gutowski, F. Chhel, J.‑P. Briot : “Byte Pair Encoding for Symbolic Music”, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, Singapore, pp. 2001-2020, (Association for Computational Linguistics) (2023)
- N. Fradet, N. Gutowski, F. Chhel, J.‑P. Briot : “Impact of time and note duration tokenizations on deep learning symbolic music modeling”, Proceedings of the 24th Conference of the International Society for Music Information Retrieval (ISMIR) 2023, Milano, Italy, pp. 89-97, (ISMIR), (ISBN: 978-1-7327299-3-3) (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)