arXiv:2606. 14120v1 Announce Type: cross Abstract: Auditory attention decoding (AAD) aims to infer the attended speaker from neural responses in multi-speaker acoustic environments and is a key problem for neuro-steered hearing systems.
NeuroCodec is a novel generative framework that uses EEG signals to guide target speaker extraction in multi‑talker environments. It operates in the latent space of a neural audio codec, modeling EEG spatial dependencies with graph convolutions and fusing EEG and speech representations via attention and Mamba‑based temporal modeling. A six‑phase training curriculum and a causal streaming version enable high‑fidelity, 44.1 kHz audio reconstruction up to 20 kHz, outperforming baselines on Cocktail Party and KUL datasets and receiving higher perceptual scores in a listening test.
The paper presents a transformer-based framework for detecting schizophrenia from EEG signals. It converts preprocessed EEG recordings into spectrograms via Short-Time Fourier Transform and classifies them using both traditional machine learning algorithms and deep learning models, including CNN-Transformer hybrids. Subject-level data partitioning ensures reliable evaluation, yielding an AUC-ROC of 88.41% for the CNN-Transformer model and 92.88% for the CNN + Squeeze and Excitation + Transformer model on an independent test set.
arXiv:2607. 09543v1 Announce Type: new Abstract: Self-supervised pretrained foundation models (FM) have shown early promise for non-invasive electroencephalogram (EEG) decoding applications.
The paper introduces a deep learning framework that uses a CNN‑GRU architecture to classify EEG recordings into resting or cognitive states. Time‑frequency analysis extracts salient signal features, which are then evaluated with both deep learning and traditional machine learning classifiers. The proposed method achieves accuracies of 83.177% for resting vs. mathematical tasks, 76.107% for resting vs. memory tasks, and 83.432% for resting vs. music tasks, outperforming comparative approaches.
arXiv:2607. 18345v1 Announce Type: cross Abstract: Limited training data constrains deep learning models for Auditory Attention Decoding (AAD) in hearing aids (HAs).
arXiv:2509. 17920v2 Announce Type: replace Abstract: Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability.
The paper introduces a deep learning framework that uses a CNN‑GRU architecture to classify EEG recordings into resting and various cognitive states. Time‑frequency analysis is applied to extract salient signal features, which are then evaluated with both deep learning and traditional machine learning classifiers, including a proposed 2D‑Net. The method achieves accuracies of 83.177% for resting vs. mathematical tasks, 76.107% for resting vs. memory tasks, and 83.432% for resting vs. music tasks, outperforming comparative approaches.
arXiv:2506.20354v3 Announce Type: replace-cross Abstract: Learning from multi-variate time-series with heterogeneous channel configurations remains a fundamental challenge for deep neural networks, p...
arXiv:2501. 09700v2 Announce Type: replace-cross Abstract: Electroencephalogram (EEG) signals have emerged as a promising modality for biometric identification.
AFA‑Net introduces a differential attention mechanism to improve Auditory Attention Detection (AAD) from EEG signals, explicitly targeting noisy data. The framework outperforms existing deep learning models, achieving 96.8% accuracy within a 2‑second decision window while using fewer parameters. It represents one of the first approaches to actively mitigate EEG noise in AAD tasks.
BrainCodes is a lightweight EEG foundation model that uses a quantization-based neural tokenizer and a spatiotemporal encoder to learn transferable EEG features from over 800 hours of data across more than 1,000 participants. The model is pretrained with a self‑supervised objective that encourages spatial connectivity and sensitivity to narrowband neural oscillations, enabling it to match or surpass state‑of‑the‑art performance on tasks such as sleep staging, attention assessment, and cognitive load estimation. It achieves these results while using up to 97% fewer trainable parameters, making it suitable for low‑resource wearable devices, and its evaluation framework analyzes the geometry and invariances of the learned representations.