# EEG2Mel: Reconstructing Sound from Brain Responses to Music

arXiv: https://arxiv.org/abs/2207.13845 · HTML: https://mlsanity.com/paper/2207.13845/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 28 Jul 2022.

## Builds on (most cited first, 7 of 7)

- [Deep Learning Human Mind for Automated Visual Classification](https://mlsanity.com/paper/1609.00344/) (2016)
- [End-to-End Auditory Object Recognition via Inception Nucleus](https://mlsanity.com/paper/2005.12195/) (2020)
- [GuessTheMusic: Song Identification from Electroencephalography response](https://mlsanity.com/paper/2009.08793/) (2020)
- [Classification of auditory stimuli from EEG signals with a regulated recurrent neural network reservoir](https://mlsanity.com/paper/1804.10322/) (2018)
- [Deep Learning of Human Perception in Audio Event Classification](https://mlsanity.com/paper/1809.00502/) (2018)
- [Mind the beat: detecting audio onsets from EEG recordings of music listening](https://mlsanity.com/paper/2102.06393/) (2021)
- [Image-based eeg classification of brain responses to song recordings](https://mlsanity.com/paper/2202.03265/) (2022)

## Built on by (most cited first, 3 of 3)

- [Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings](https://mlsanity.com/paper/2412.15560/) (2024)
- [A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond](https://mlsanity.com/paper/2502.12048/) (2025)
- [Channel-Preserving Representation Alignment for EEG-to-Music Reconstruction](https://mlsanity.com/paper/2606.04040/) (2026)

## Abstract (arXiv)

Information retrieval from brain responses to auditory and visual stimuli has shown success through classification of song names and image classes presented to participants while recording EEG signals. Information retrieval in the form of reconstructing auditory stimuli has also shown some success, but here we improve on previous methods by reconstructing music stimuli well enough to be perceived and identified independently. Furthermore, deep learning models were trained on time-aligned music stimuli spectrum for each corresponding one-second window of EEG recording, which greatly reduces feature extraction steps needed when compared to prior studies. The NMED-Tempo and NMED-Hindi datasets of participants passively listening to full length songs were used to train and validate Convolutional Neural Network (CNN) regressors. The efficacy of raw voltage versus power spectrum inputs and linear versus mel spectrogram outputs were tested, and all inputs and outputs were converted into 2D images. The quality of reconstructed spectrograms was assessed by training classifiers which showed 81% accuracy for mel-spectrograms and 72% for linear spectrograms (10% chance accuracy). Lastly, reconstructions of auditory music stimuli were discriminated by listeners at an 85% success rate (50% chance) in a two-alternative match-to-sample task.