Article

A generalizable speech neuroprosthesis

2026-07-27

Abstract excerpt

Intracortical brain-computer interfaces (BCIs) can restore communication to people with vocal tract paralysis by decoding cortical activity during attempted speech into text. State-of-the-art systems pairing neural-to-phoneme decoders with phoneme-to-word language models have achieved word error rates (WERs) as low as 1%, but only after collecting thousands of sentences of training data. Shortening the data collec...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: aaad616c-799d-52d1-a978-9bc40b0e4b16
DOI: 10.64898/2026.07.23.739430

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

A generalizable speech neuroprosthesisDOI 10.64898/2026.07.23.739430Read

A Neural Speech Decoding Framework Leveraging Deep Learning and Speech SynthesisSemantic proximity Read

Subject-Agnostic Transformer-Based Neural Speech Decoding from Surface and Depth Electrode SignalsSemantic proximity Read

Cross-subject decoding of human neural data for speech Brain Computer InterfacesSemantic proximity Read

Non-Invasive Brain-to-Text BCIs: Phoneme-Level Sentence Reconstruction from MEGSemantic proximity Read

A Novel Machine Learning Model for Non-Invasive EEG-Based Inner-Speech Translation in ALSSemantic proximity Read

A Novel Machine Learning Model for Non-Invasive EEG-Based Inner-Speech Translation in ALSSemantic proximity Read

Large Language Models Integrated into Brain-Computer Interfaces for Communication and Control: A Systematic ReviewSemantic proximity Read

Intelligible speech synthesis from neural decoding of spoken sentencesSemantic proximity Read

Cross-brain transfer of high-performance intracortical speech and handwriting BCIsSemantic proximity Read

Towards Unified Neural Decoding with Brain Functional Network ModelingSemantic proximity Read

Near-Optimal P300 Speller Performance Using Large Language Models: A Multi-Model Analysis with Performance BoundsSemantic proximity Read

Reconstructing the brain’s language network from non-invasive EEG enables interpretable speech decodingSemantic proximity Read