Research Projects
OpenTuning
Individuation créative par le design d'interaction avec des systèmes musicaux génératifs
Dates : March 2026 to December 2029
Inside Artificial Improvisation
Dans la boîte noire de l’improvisation artificielle
Dates : January 2026 to December 2029
INTIM
INteractive analysis/synthesis of musical TIMbre
Dates : September 2024 to March 2026
PostGenAI@Paris
Projet ayant pour ambition de renforcer la stratégie française en intelligence artificielle en créant un pôle d’excellence international spécialisé dans l’IA post-générative
Dates : January 2025 to December 2029
Koral
Playing music collectively using smartphones
Dates : December 2023 to December 2024
EVA
Explicite Voice Attributes
Dates : October 2023 to January 2028
ReNAR
Reducing Noise with Augmented Reality
Dates : October 2023 to March 2028
Axe Son-Musique-Santé
This cross-cutting Sound–Music & Health strand brings together research related to wellbeing and health conducted within the STMS laboratory.
DeTOX
Lutte contre les vidéos hyper-truquées de personnalités françaises
Dates : January 2023 to December 2025
REVOLT
REvealing human bias with real Time VOcal deep fakes
Dates : January 2021 to December 2023
Synthesis of Directionality by Corpus
Aaron Einbond's artistic residency focuses on the cohabitation of instrumental and synthetic sounds in a diffusion space.The playing of an instrumentalist on stage is captured and analyzed in real time: different audio descriptors (timbral) are computed and exploited to produce electronics by concatenative synthesis by corpus (realized by CataRT-MuBu). The question of the diffusion of the samples (grains) of the corpus is then raised. For this purpose, we use a compact array of IKO loudspeakers, which allows us to simulate radiation patterns (described by their representation in third order spherical harmonics). The radiation patterns used here are selected from a directivity database of (historical and modern) acoustic instruments measured and made available by TU Berlin: the audio descriptors (from the player's playing) are used to select one (or more) instruments from the TU database in order to apply their directivity pattern to the grains. The underlying idea is not to faithfully reproduce the spatial radiation of instruments, but to give the synthesized sounds a "natural, plausible" spatiality, so that the electronics merge harmoniously with the acoustic instruments present on stage.
RAMHO
Musical Research and Acoustics in France after 1945: An Oral History

