Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria

Moses, David A.; Metzger, Sean; Liu, Jessie R.; Anumanchipalli, Gopala K.; Makin, Joseph G.; Sun, Pengfei; Chartier, Josh; Dougherty, Max; Liu, Patricia M; Abrams, Gary; Tu-Chan, Adelyn; Ganguly, Karunesh; Chang, Edward F.

doi:10.1056/nejmoa2027540

Cited by 285 publications

(330 citation statements)

References 35 publications

Supporting

Mentioning

261

Contrasting

Unclassified

Order By: Relevance

“…These results suggest that it might prove difficult to successfully transfer the decoding process of brain-computer interfaces trained with overt or even silently articulated speech to imagined speech 2 , 4 , 5 . BHA representations were poorly discriminant in primary sensory and motor regions during the imagined speech, in accord with the flexible abstraction hypothesis of imagined speech, suggesting that BHA might not be a good feature for imagined speech decoding.…”

Section: Discussionmentioning

confidence: 99%

“…a robotic arm 1 . One approach to decode imagined speech is to train algorithms on neural activity corresponding to articulatory motor commands produced during overt or silently articulated speech, hoping that the learned features could ultimately be transferred to patients who are unable to speak 2 – 5 . Although potentially interesting, this hypothesis is limited in scope as it can only apply to cases where language and cortical motor commands are preserved (such as in motor neuron disease), i.e.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2022

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%

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Considering the high number of S protein mutations that the P.1 variant has accumulated, it is reasonable to conclude that it will be equally or even more resistant than the B.1.351 variant to antibody-mediated protection. Laboratory serum neutralization assays using a pseudovirus have shown that the neutralizing activity of BNT162b2-elicited antibodies to B.1.1.7-spike virus and P.1-spike virus is approximately equivalent 53 . A trial in Brazil using the CoronaVac (Sinovac Biotech) vaccine showed an efficacy of 50% against symptomatic infection (just above the approval threshold for emergency use) in 12,508 volunteers, all of whom were health-care professionals in regular direct contact with SARS-CoV-2 (ref.…”

Section: Effects Of Viral Variantsmentioning

confidence: 99%

Progress of the COVID-19 vaccine effort: viruses, vaccines and variants versus efficacy, effectiveness and escape

et al. 2021

View full text Add to dashboard Cite

Where 2020 saw the development and testing of vaccines against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) at an unprecedented pace, the first half of 2021 has seen vaccine rollout in many countries. In this Progress article, we provide a snapshot of ongoing vaccine efficacy studies, as well as real-world data on vaccine effectiveness and the impact of virus variants of concern. Where they have been deployed in a high proportion of the adult population, the currently approved vaccines have been extremely effective in preventing COVID-19, particularly severe disease. Nonetheless, there are still significant challenges in ensuring equitable vaccine access around the globe and lessons that can be learned for controlling this pandemic and for the next pandemic.

show abstract

“…In the many species in which we do not have access to a biophysical model of vocal production, learned acoustic spaces may be a viable alternative. In contrast, the current state-of-the-art vocal prostheses for speech bypass biophysical models, directly predicting sentences (i.e., symbolic sequences) with the aid of language models (i.e., a sequence model) (Moses et al, 2021 ). Such methods do not capture important extra-linguistic information such as emotional tone and stress.…”

Section: Mapping Vocal Communication To Perception Behavior and Physiologymentioning

confidence: 99%

Toward a Computational Neuroethology of Vocal Communication: From Bioacoustics to Neurophysiology, Emerging Tools and Future Directions

Sainburg

Gentner

2021

Front. Behav. Neurosci.

View full text Add to dashboard Cite

Recently developed methods in computational neuroethology have enabled increasingly detailed and comprehensive quantification of animal movements and behavioral kinematics. Vocal communication behavior is well poised for application of similar large-scale quantification methods in the service of physiological and ethological studies. This review describes emerging techniques that can be applied to acoustic and vocal communication signals with the goal of enabling study beyond a small number of model species. We review a range of modern computational methods for bioacoustics, signal processing, and brain-behavior mapping. Along with a discussion of recent advances and techniques, we include challenges and broader goals in establishing a framework for the computational neuroethology of vocal communication.

show abstract

Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria

Cited by 285 publications

References 35 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

Progress of the COVID-19 vaccine effort: viruses, vaccines and variants versus efficacy, effectiveness and escape

Toward a Computational Neuroethology of Vocal Communication: From Bioacoustics to Neurophysiology, Emerging Tools and Future Directions

Contact Info

Product

Resources

About