Author

Feng Tian

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Joint Text-Audio Alignment for EEG-to-Text Decoding in Chinese Speech Production and Perception

EEAlign is introduced, a novel parameter-efficient framework that jointly aligns EEG with two axes---text alignment with BGE-M3 text embeddings and audio alignment with wav2vec~2.0 speech features via contrastive learning followed by CTC character-sequence decoding.

Tian Zheng, Xu-Rong Xie, Xinxin Zhu et al. · arXiv.org · 0 citations