MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors

ArXi:2605.31173v1 Announce Type: cross Reconstructing continuous speech from non-invasive neural recordings is a fundamental problem for probing human auditory perception and building safe, scalable speech brain-computer interfaces. Despite recent progress, intelligible reconstruction remains elusive, as non-invasive recordings are inherently noisy, spatially blurred, and only partially preserve information about perceived speech.