Guangyin Bao
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Sound×1AI×1
Frequent co-authors
Research Timeline
2026
MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors
MindVoice is a neuro-to-speech framework that uses pretrained priors to disentangle and reconstruct intelligible speech from noisy, non-invasive neural signals, significantly outperforming existing methods.
Highlighted terms show continued research focus across papers