Brain2Music: Reconstructing Music from Human Brain Activity
Abstract
The process of reconstructing experiences from human brain activity offers a unique lens into how the brain interprets and represents the world. In this paper, we introduce a method for reconstructing music from brain activity, captured using functional magnetic resonance imaging (fMRI). Our approach uses either music retrieval or the MusicLM music generation model conditioned on embeddings derived from fMRI data. The generated music resembles the musical stimuli that human subjects experienced, with respect to semantic properties like genre, instrumentation, and mood. We investigate the relationship between different components of MusicLM and brain activity through a voxel-wise encoding modeling analysis. Furthermore, we discuss which brain regions represent information derived from purely textual descriptions of music stimuli. We provide supplementary material including examples of the reconstructed music at https://google-research.github.io/seanet/brain2music
Cite
@article{arxiv.2307.11078,
title = {Brain2Music: Reconstructing Music from Human Brain Activity},
author = {Timo I. Denk and Yu Takagi and Takuya Matsuyama and Andrea Agostinelli and Tomoya Nakai and Christian Frank and Shinji Nishimoto},
journal= {arXiv preprint arXiv:2307.11078},
year = {2026}
}
Comments
Preprint; 21 pages; supplementary material: https://google-research.github.io/seanet/brain2music