Stage M2 – Brass instrument bore optimization via Machine Learning and physics-based sound simulations

Sound simulations by physical models are interesting to transcribe the physics underlying the functioning of a musical instrument. These simulations make it possible to listen to a virtual instrument with a mode of operation representative of the interaction musician/instrument (driving a sound by the causes that create it). The work consists in studying the contribution of machine learning methods in the understanding of the relationships between the shape of an instrument and the sound produced, in order to « optimize » the shape of an instrument according to different perceptual dimensions (intonation, ease of emission, dimensions of timbre, etc.). The application concerns the brass instruments (trumpet, trombone). The method could be interesting to assist instrument making and to customize instruments. A partnership with Yamaha corporation (Japan) is planned in the frame of the internship. Yamaha will provide different case studies and the development of prototypes.

More informations on the link below.