Brain Recording, Mind-Reading, and Neurotechnology: Ethical Issues from Consumer Devices to Brain-Based Speech Decoding

Rainey, Stephen; Martin, Stéphanie; Christen, Andy; Mégevand, Pierre; Fourneret, Éric

doi:10.1007/s11948-020-00218-0

Cited by 26 publications

(15 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adding more features, and especially higher-level ones could also help addressing the ethical question of which part exactly of the imagined speech should we let machines decode 68 . Finally, decoding performance will likely dramatically increase when using on-line systems where both the subject and the algorithm learn simultaneously, which so far is difficult to envisage in patients who are implanted over a short time span as in epilepsy.…”

Section: Discussionmentioning

confidence: 99%

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features

et al. 2022

Self Cite

View full text Add to dashboard Cite

Reconstructing intended speech from neural activity using brain-computer interfaces holds great promises for people with severe speech production deficits. While decoding overt speech has progressed, decoding imagined speech has met limited success, mainly because the associated neural signals are weak and variable compared to overt speech, hence difficult to decode by learning algorithms. We obtained three electrocorticography datasets from 13 patients, with electrodes implanted for epilepsy evaluation, who performed overt and imagined speech production tasks. Based on recent theories of speech neural processing, we extracted consistent and specific neural features usable for future brain computer interfaces, and assessed their performance to discriminate speech items in articulatory, phonetic, and vocalic representation spaces. While high-frequency activity provided the best signal for overt speech, both low- and higher-frequency power and local cross-frequency contributed to imagined speech decoding, in particular in phonetic and vocalic, i.e. perceptual, spaces. These findings show that low-frequency power and cross-frequency dynamics contain key information for imagined speech decoding.

show abstract

Section: Discussionmentioning

confidence: 99%

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

“…We are just beginning to use machine learning and BCI systems for language restoration, and significant progress can be expected in the coming years, which will lead to unprecedented questions. Among them, the issue of which part exactly of the imagined speech should we let machines decode should trigger careful ethical reflections, which we must conduct ahead of time to prevent abuses and legal loopholes (Rainey et al, 2020). This and other debates, for instance regarding the privacy of neural data, necessitate a multidisciplinary approach that goes beyond the purely technical neuroengineering problem, and pose a challenge that calls for a common effort that we hope scientists will tackle as a community.…”

Section: Discussionmentioning

confidence: 99%

Imagined speech can be decoded from low- and cross-frequency features in perceptual space

Proix

Christen

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

SummaryReconstructing intended speech from neural activity using brain-computer interfaces (BCIs) holds great promises for people with severe speech production deficits. While decoding overt speech has progressed, decoding imagined speech have met limited success, mainly because the associated neural signals are weak and variable hence difficult to decode by learning algorithms. Using three electrocorticography datasets totalizing 1444 electrodes from 13 patients who performed overt and imagined speech production tasks, and based on recent theories of speech neural processing, we extracted consistent and specific neural features usable for future BCIs, and assessed their performance to discriminate speech items in articulatory, phonetic, vocalic, and semantic representation spaces. While high-frequency activity provided the best signal for overt speech, both low- and higher-frequency power and local cross-frequency contributed to successful imagined speech decoding, in particular in phonetic and vocalic, i.e. perceptual, spaces. These findings demonstrate that low-frequency power and cross-frequency dynamics contain key information for imagined speech decoding, and that exploring perceptual spaces offers a promising avenue for future imagined speech BCIs.

show abstract

“…This implies to examine closely the ethical and legal issues of the use of these technologies, which will affect an increasing audience. The capacity of NT to “manipulate the brains” calls for vigilance in two particular areas: respect of mental autonomy and protection of brain data ( Ienca and Andorno, 2017 ; Yuste et al, 2017 ; Minielly et al, 2020 ; Rainey et al, 2020 ; Pfotenhauer et al, 2021 ):…”

Section: The Ethical Legal and Societal Challenges Of Ntsmentioning

confidence: 99%

Neurotechnologies under the Eye of Bioethics

Vidal

2022

eNeuro

View full text Add to dashboard Cite

Brain Recording, Mind-Reading, and Neurotechnology: Ethical Issues from Consumer Devices to Brain-Based Speech Decoding

Cited by 26 publications

References 36 publications

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features

Imagined speech can be decoded from low- and cross-frequency features in perceptual space

Neurotechnologies under the Eye of Bioethics

Contact Info

Product

Resources

About