Naturalistic Music Decoding from EEG Data via Latent Diffusion Models

TL;DR

This paper investigates reconstructing complex, naturalistic music from EEG data using latent diffusion models, demonstrating a novel approach to neural decoding of rich auditory experiences.

Contribution

It introduces a new end-to-end method employing latent diffusion models for high-quality music reconstruction directly from raw EEG data, without manual pre-processing.

Findings

Successful reconstruction of complex music from EEG signals.

Use of neural embedding-based metrics for evaluation.

First application of diffusion models to EEG-based music decoding.

Abstract

In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroencephalogram (EEG) recordings. Unlike simpler music with limited timbres, such as MIDI-generated tunes or monophonic pieces, the focus here is on intricate music featuring a diverse array of instruments, voices, and effects, rich in harmonics and timbre. This study represents an initial foray into achieving general music reconstruction of high-quality using non-invasive EEG data, employing an end-to-end training approach directly on raw data without the need for manual pre-processing and channel selection. We train our models on the public NMED-T dataset and perform quantitative evaluation proposing neural embedding-based metrics. Our work contributes to the ongoing research in neural decoding and brain-computer interfaces, offering insights into the feasibility of using EEG data for complex auditory information reconstruction.