# Frank Willett **Entity class:** Person **Domain:** Speech Neuroprostheses / Neural Decoding **Doc Type:** Person Node **Maturity:** Developed **Collection:** [[collections/Neurotech|Neurotech]] **Primary Sources:** *Cell*, 14 August 2025 ## Definition **Frank Willett is assistant professor of neurosurgery at [[wiki/Stanford University|Stanford]] and co-director of its Neural Prosthetics Translational Laboratory, and the senior author of the study that first decoded inner speech in humans.** He previously held a research-scientist position at Stanford and the Howard Hughes Medical Institute. His work sits inside the [[wiki/BrainGate|BrainGate]] consortium directed by Leigh Hochberg. ## Work in the corpus - **[[wiki/Inner Speech Decoding|Inner speech decoding]]** (*Cell*, 14 August 2025), with lead author Erin Kunz and Benyamin Meschede-Krasa: silently imagined sentences decoded from motor-cortex arrays in four participants with ALS or brainstem stroke, at up to 74% accuracy against a vocabulary of up to 125,000 words, a word error rate as low as 26%. - **The thought-password gate:** decoding began only after the participant silently imagined a chosen phrase, recognized above 98%. Willett's team built an access-control layer into the device before any statute required one, which the register reads as the first implemented instance of cognitive access control. - **The privacy finding:** while participants silently counted shapes, the decoder produced number sequences, showing that task-related inner speech is readable without an instruction to communicate. ## Reading Willett's stated goal is fluent, rapid and comfortable speech restoration through inner speech alone. The corpus reads his result as the point at which the read channel reached genuinely private content, and as the clearest example of the register's claim that recent gains belong to the decoder rather than the sensor: the arrays are the same class used for years, and the capability changed on the model side. ## Research Inferences These entries translate the forward-looking register in [[research/Research Inferences|Research Inferences]] into ordinary wiki prose. The tier labels apply to the inference, not automatically to every factual anchor inside it. Proposed IDs above INF-0500 come from the 2026-10-23 cycle: [[research/Research Inferences Integration Report - 2026-10-23|Research Inferences Integration Report — 2026-10-23]] · [[research/Research Inferences Integration Audit - 2026-10-23|Research Inferences Integration Audit — 2026-10-23]]. - **INF-0083 — Strongly indicated.** Work through 2026 has moved from decoding externally supplied captions toward recovering participants' own inner speech via subject-specific neural-semantic alignment. Inner speech is the first genuinely private content to become instrumentable, and the technique requires no change to the underlying language model. - **INF-0007 — Strongly indicated.** Academic speech BCIs reached 62–78 words per minute with implanted electrodes and model-side decoding, which means the recent gains are attributable to the decoder more than the sensor. Decoder improvement is free of surgical risk and compounds across every existing implant already in a head. - **INF-0086 — Strongly indicated.** Semantic decoding from non-invasive recordings requires cooperation today, and that requirement is a property of current signal quality rather than a principle. Legal frameworks built on the assumption of required cooperation are therefore built on a moving quantity. - **INF-0386 — Strongly indicated.** Coupled cognition requires an access-control model specifying who may read which internal state under what conditions. Access control is a solved discipline in computing, and importing it wholesale is the fastest route to safe coupling. - **INF-0096 — Strongly indicated.** Restoring speech with a synthesized version of the person's own pre-morbid voice is already technically routine. The restored person therefore speaks in a voice generated from a model, and the resulting identity object is part biological, part trained artifact. ## Relationships - **institution:** [[wiki/Stanford University|Stanford University]]; co-director, Neural Prosthetics Translational Laboratory. - **program:** [[wiki/BrainGate|BrainGate]] (BrainGate2 clinical trial, directed by Leigh Hochberg). - **senior_author_of:** [[wiki/Inner Speech Decoding|Inner Speech Decoding]] (*Cell*, 2025), with Erin Kunz as lead author. - **field_peers:** [[wiki/Edward Chang|Edward Chang]] · [[wiki/Sergey Stavisky|Sergey Stavisky]] · [[wiki/Matthew Willsey|Matthew Willsey]]. - **capability_class:** [[wiki/Speech Neuroprosthesis|Speech Neuroprosthesis]] · [[wiki/Semantic Neural Decoding|Semantic Neural Decoding]]. - **population:** [[wiki/Amyotrophic Lateral Sclerosis|Amyotrophic Lateral Sclerosis]] · [[wiki/Locked-In Syndrome|Locked-In Syndrome]]. - **governance_consequence:** [[wiki/Neurorights|Neurorights]] · [[wiki/Mental Privacy|Mental Privacy]]. - **ecosystem:** [[collections/Neurotech|Neurotech]]. ## Sources - [Study of promising speech-enabling interface — Stanford Medicine, August 2025](https://med.stanford.edu/news/all-news/2025/08/brain-computer-interface.html) - [Brain-computer interface lets users communicate using thoughts — The Scientist, 2025](https://www.the-scientist.com/brain-computer-interface-lets-users-communicate-using-thoughts-73275) - [These brain implants speak your mind, even when you don't want to — NPR, 20 August 2025](https://www.gpb.org/news/shots-health-news/2025/08/20/these-brain-implants-speak-your-mind-even-when-you-dont-want) As of 23 October 2026.