UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
A high-performance speech neuroprosthesis.Nature, 620(7976):1031–1036
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
EMG signals from orofacial muscles are mapped via linear transformation into self-supervised speech representation space to enable direct audio synthesis, shown on an ALS patient during silent articulation.
Direct sequence-to-sequence EMG-to-text conversion for silent articulation using a geometric representation of high-dimensional signals, without audio targets or time-alignment.
citing papers explorer
-
UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
-
emg2speech: Synthesizing speech from electromyography using self-supervised speech models
EMG signals from orofacial muscles are mapped via linear transformation into self-supervised speech representation space to enable direct audio synthesis, shown on an ALS patient during silent articulation.
-
Non-invasive electromyographic speech neuroprosthesis: a geometric perspective
Direct sequence-to-sequence EMG-to-text conversion for silent articulation using a geometric representation of high-dimensional signals, without audio targets or time-alignment.