Loading
What changed between revision 1 and revision 2, compared over the article's markdown source with its frontmatter — so a change to status, evidence or reversibility shows up as the edit it is.
Older · revision 1
Import· initial corpus import, not an edit
Initial import of content/speech-neuroprosthesis.md — the filesystem corpus, unchanged. Not an edit.
12.1 kB
Revision 1
Revision 2
lines 8–18 → 8–177 unchanged lines not shown
categories: ["cybernetics"]categories: ["cybernetics"]tags: ["bci", "speech decoding", "als", "anarthria", "neural decoding", "communication"]tags: ["bci", "speech decoding", "als", "anarthria", "neural decoding", "communication"]summary: "A brain–computer interface that reconstructs intended speech from motor cortex activity, producing text or synthesized voice for people who cannot speak."summary: "A brain–computer interface that reconstructs intended speech from motor cortex activity, producing text or synthesized voice for people who cannot speak."updated: "2026-07-27"updated: "2026-08-23"humanEvidence: "Published results come from one or a few implanted participants, mostly with ALS or brainstem stroke; no multi-participant efficacy trial has been run and no device is approved anywhere."humanEvidence: "Published results come from one or a few implanted participants, mostly with ALS or brainstem stroke; no multi-participant efficacy trial has been run and no device is approved anywhere."access: "Not obtainable: a handful of research implants at academic centres under investigational device exemptions, with no approved or purchasable system."access: "Not obtainable: a handful of research implants at academic centres under investigational device exemptions, with no approved or purchasable system."reversibility: "difficult"reversibility: "difficult"issues: ["The 2024 UC Davis result is given as accuracy only; no words-per-minute figure is stated."]------ ```infobox```infoboxlines 95–104 → 94–10576 unchanged lines not shown
face.[^metzger2023]face.[^metzger2023] A 2024 report from a UC Davis and Brown collaboration pushed accuracy rather than speed, reportingA 2024 report from a UC Davis and Brown collaboration pushed accuracy rather than speed, reportingword accuracy near 98 percent over a very large vocabulary in a participant with ALS, with the97.5 percent word accuracy over a 125,000-word vocabulary sustained across 8.4 months in asystem usable from the first session and improving over months of daily self-directedparticipant with ALS, with the system usable from the first session. The rate in self-paceduse.[^card2024] Subsequent work has attacked latency: streaming architectures that emit words asconversation was about 32 words per minute over more than 248 cumulative hours — slower than eitherthey are formed rather than at the end of a sentence, and voice synthesis fast enough to preserve2023 result.[^card2024] Subsequent work has attacked latency: streaming architectures that emitwords as they are formed rather than at the end of a sentence, and voice synthesis fast enough topreserveconversational turn-taking and some prosody.[^littlejohn2025]conversational turn-taking and some prosody.[^littlejohn2025] A related line uses imagined handwriting rather than speech. Decoding attempted pen strokes fromA related line uses imagined handwriting rather than speech. Decoding attempted pen strokes fromlines 129–134 → 130–14624 unchanged lines not shown
hippocampal work described under [[memory-prosthesis]] — report effects that are small, contested,hippocampal work described under [[memory-prosthesis]] — report effects that are small, contested,and difficult to evaluate precisely because there is no equivalent of a transcript to score.and difficult to evaluate precisely because there is no equivalent of a transcript to score. > [!caution] Every headline figure is one person's decoder> The 2021, 2023 and 2024 results each come from a single implanted participant, and the largest> group in any speech-decoding paper is the four BrainGate2 participants — T12, T15, T16 and T17 —> reported together in 2025.[^kunz2025] Each decoder is trained on that individual's own attempted> speech and does not transfer: models trained jointly across participants have appeared only> recently, and they still align each new person's cortex into the shared space with a per-subject> transform.[^boccato2026] BrainGate2 is a registered feasibility study, so the published figures> describe individuals rather than a cohort, and there is no denominator for how often an implant> reaches conversational performance. A trial that reported performance for every participant it> enrolled would supply one. ## Inner speech and privacy## Inner speech and privacy The obvious worry — that a device might transcribe thoughts a person did not choose to utter — isThe obvious worry — that a device might transcribe thoughts a person did not choose to utter — islines 193–196 → 205–21058 unchanged lines not shown
[^littlejohn2025]: `paper` Littlejohn, K. T. et al. "A streaming brain-to-voice neuroprosthesis to restore naturalistic communication." *Nature Neuroscience*, 2025.[^littlejohn2025]: `paper` Littlejohn, K. T. et al. "A streaming brain-to-voice neuroprosthesis to restore naturalistic communication." *Nature Neuroscience*, 2025. [^kunz2025]: `paper` Kunz, E. M. et al. "Inner speech in motor cortex and implications for speech neuroprostheses." *Cell*, 2025. {The password-gated mode is a laboratory demonstration in already implanted research participants, not a safeguard validated in any deployed device.}[^kunz2025]: `paper` Kunz, E. M. et al. "Inner speech in motor cortex and implications for speech neuroprostheses." *Cell*, 2025. {The password-gated mode is a laboratory demonstration in already implanted research participants, not a safeguard validated in any deployed device.} [^boccato2026]: `paper` Boccato, T., Olak, M. and Ferrante, M. "Cross-subject decoding of human neural data for speech brain–computer interfaces." *Journal of Neural Engineering*, 2026. {A reanalysis of the two largest public intracortical speech datasets, so its own sample is four participants; the authors name that as the study's fundamental limitation.} removed, struck through added, underlinedLine numbers count the serialised markdown of each revision, frontmatter included.
190 lines are the same in both revisions, and 165 of them are not shown. Neither revision here is necessarily the current article — read Speech neuroprosthesis for the text this wiki stands behind today.