Proceedings Abstracts of the Twenty-Fourth International Joint Conference on Artificial Intelligence

Capturing a Musician's Groove: Generation of Realistic Accompaniments from Single Song Recordings / 4140
Mathieu Ramona, Giordano Cabral, François Pachet

This demonstration presents a concatenative synthesis engine for the generation of musical accompaniments, based on chord progressions. The system takes a player's song recording as input, and generates the accompaniment for any other song, based on the input content. We show that working on accompaniment requires a special care about temporal deviations at the border of the sliced chunks, because they make most of the rhythmic groove. We address it by discriminating accidental deviations against intentional ones, in order to correct the first while keeping the second. We will provide a full demonstration of the system, from the recording process to the generation, in various conditions, inviting the audience to participate.