To investigate the processing of speech in the brain, simple linear models are commonly used to establish a relationship between brain signals and speech features. However, these linear models are ill-equipped to model a highly dynamic and complex non-linear system like the brain. Although non-linear methods with neural networks have been developed recently, reconstructing unseen stimuli from unseen subjects' EEG is still a highly challenging task. This work presents a novel method, ConvConcatNet, to reconstruct mel-specgrams from EEG, in which the deep convolution neural network and extensive concatenation operation were combined. With our ConvConcatNet model, the Pearson correlation between the reconstructed and the target mel-spectrogram can achieve 0.0420, which was ranked as No.1 in the Task 2 of the Auditory EEG Challenge. The codes and models to implement our work will be available on Github: https://github.com/xuxiran/ConvConcatNet
@article{arxiv.2401.04965,
title = {ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG},
author = {Xiran Xu and Bo Wang and Yujie Yan and Haolin Zhu and Zechen Zhang and Xihong Wu and Jing Chen},
journal= {arXiv preprint arXiv:2401.04965},
year = {2024}
}