AINeutralarXiv – CS AI · 10h ago6/10
🧠
MindAlign: Decoding Inner Speech from fMRI Signals via Multimodal Embedding Alignment under Limited Data
Researchers introduce MindAlign, a two-stage framework that decodes inner speech from fMRI brain signals by aligning neural activity with semantic embeddings, then using a frozen language model for text generation. The approach demonstrates improved performance over existing methods and shows that semantic-to-language mappings can generalize across subjects, advancing scalable brain-to-text decoding technology.