PT  - JOURNAL ARTICLE
AU  - Wilson, Guy H.
AU  - Stavisky, Sergey D.
AU  - Willett, Francis R.
AU  - Avansino, Donald T.
AU  - Kelemen, Jessica N.
AU  - Hochberg, Leigh R.
AU  - Henderson, Jaimie M.
AU  - Druckmann, Shaul
AU  - Shenoy, Krishna V.
TI  - Decoding spoken English phonemes from intracortical electrode arrays in dorsal precentral gyrus
AID  - 10.1101/2020.06.30.180935
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2020.06.30.180935
4099  - http://biorxiv.org/content/early/2020/07/01/2020.06.30.180935.short
4100  - http://biorxiv.org/content/early/2020/07/01/2020.06.30.180935.full
AB  - Objective To evaluate the potential of intracortical electrode array signals for brain-computer interfaces (BCIs) to restore lost speech, we measured the performance of classifiers trained to discriminate a comprehensive basis set for speech: 39 English phonemes. We classified neural correlates of spoken-out-loud words in the “hand knob” area of precentral gyrus, which we view as a step towards the eventual goal of decoding attempted speech from ventral speech areas in patients who are unable to speak.Approach Neural and audio data were recorded while two BrainGate2 pilot clinical trial participants, each with two chronically-implanted 96-electrode arrays, spoke 420 different words that broadly sampled English phonemes. Phoneme onsets were identified from audio recordings, and their identities were then classified from neural features consisting of each electrode’s binned action potential counts or high-frequency local field potential power. We also examined two potential confounds specific to decoding overt speech: acoustic contamination of neural signals and systematic differences in labeling different phonemes’ onset times.Main results A linear decoder achieved up to 29.3% classification accuracy (chance = 6%) across 39 phonemes, while a recurrent neural network classifier achieved 33.9% accuracy. Parameter sweeps indicated that performance did not saturate when adding more electrodes or more training data, and that accuracy improved when utilizing time-varying structure in the data. Microphonic contamination and phoneme onset differences modestly increased decoding accuracy, but could be mitigated by acoustic artifact subtraction and using a neural speech onset marker, respectively.Significance The ability to decode a comprehensive set of phonemes using intracortical electrode array signals from a nontraditional speech area suggests that placing electrode arrays in ventral speech areas is a promising direction for speech BCIs.Competing Interest StatementThe MGH Translational Research Center has a clinical research support agreement with Neuralink, Paradromics, and Synchron, for which L.R.H. provides consultative input. JMH is a consultant for Neuralink Corp and Proteus Biomedical, and serves on the Medical Advisory Board of Enspire DBS. KVS consults for Neuralink Corp. and CTRL-Labs Inc. (part of Facebook Reality Labs) and is on the scientific advisory boards of MIND-X Inc., Inscopix Inc., and Heal Inc. All other authors have no competing interests.