← Back to all news
arXiv Machine Learning By Julian Silva, Jaliya Kodithuwakku, Navindu Sirimanna, Shaveen Herath, Wageesha N. Manamperi, Joshua P. Kulasingham

NeuroCodec: EEG-Guided Latent-Domain Generative Model for High-Fidelity Target Speaker Extraction

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 12

RAMamba-Net: A Reliability-Aware and Mamba-Based Multimodal Fusion Network for Auditory Attention Detection

RAMamba-Net is a new multimodal fusion network designed for auditory attention decoding (AAD) that combines EEG and electrooculography (EOG) signals. It uses a Mamba-enhanced band-aware convolutional Transformer to capture EEG band-specific patterns and long-range temporal dynamics, while a dual-branch encoder models EOG temporal and inter-channel dependencies. Cross‑modal attention and a reliability‑aware module estimate sample‑wise modality weights, improving fusion robustness and achieving a 5.76% accuracy gain over unimodal baselines on two AAD benchmarks.

By Xingyi He, Ziwei Wang, Dongrui Wu
llmsmultimodalbenchmarkssafety
More like this →
arXiv AI
Aug 25

Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings

The paper introduces a Cross-Subject Perceived Speech Decoding (CPSD) framework that tackles the challenge of decoding perceived speech from non‑invasive brain recordings across different subjects. CPSD uses a two‑stage training process: first, contrastive learning pre‑trains a source model on multiple subjects to capture shared representations; second, personal specialization fine‑tunes the model for a target subject by extracting consistent components and further training on that subject’s data. A Positional Encoding‑based Spatial Attention (PESA) module is added to remap MEG/EEG data into a standardized reference space, improving cross‑subject consistency. Evaluations on three datasets (Armeni 2022, PKUEEG 2025, Broderick 2018) show that CPSD outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top‑10 accuracy, demonstrating its effectiveness, efficiency, and robustness.

By Aoke Zhang, Bo Wang, Xihong Wu, Heping Cheng, Jing Chen
fine-tuning
More like this →