Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria.

@article{Moses2021NeuroprosthesisFD,
  title={Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria.},
  author={David A. Moses and Sean L. Metzger and Jessie R. Liu and Gopala K. Anumanchipalli and Joseph G. Makin and Pengfei F Sun and Josh Chartier and Maximilian E. Dougherty and Patricia M Liu and Gary M. Abrams and Adelyn Tu-Chan and Karunesh Ganguly and Edward F. Chang},
  journal={The New England journal of medicine},
  year={2021},
  volume={385 3},
  pages={
          217-227
        }
}
BACKGROUND Technology to restore the ability to communicate in paralyzed persons who cannot speak has the potential to improve autonomy and quality of life. An approach that decodes words and sentences directly from the cerebral cortical activity of such patients may represent an advancement over existing methods for assisted communication. METHODS We implanted a subdural, high-density, multielectrode array over the area of the sensorimotor cortex that controls speech in a person with… 

Figures from this paper

Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework

TLDR
These results demonstrate that intracranial depth electrodes can be used to synthesize audio, despite the suboptimal sampling across many brain regions instead of the focused sampling of relevant areas provided by ECoG.

Decoding speech from non-invasive brain recordings

TLDR
A single end-to-end architecture trained with contrastive learning across a large cohort of individuals to predict self-supervised representations of natural speech is proposed, delineate a promising path to decode natural language processing in real time from non-invasive recordings of brain activity.

Speech Production in Intracranial Electroencephalography: iBIDS Dataset

TLDR
A dataset of 10 participants reading out individual words while the authors measured intracranial EEG from a total of 1103 electrodes can help in understanding the speech production process better and can be used to test speech decoding and synthesis approaches from neural data to develop speech Brain-Computer Interfaces and speech neuroprostheses.

Dataset of Speech Production in intracranial Electroencephalography

Speech production is an intricate process involving a large number of muscles and cognitive processes. The neural processes underlying speech production are not completely understood. As speech is a

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

TLDR
It is demonstrated using human intracranial recordings that both low- and higher-frequency power and local cross-frequency contribute to imagined speech decoding, in particular in phonetic and vocalic spaces.

Decoding grasp and speech signals from the cortical grasp circuit in a tetraplegic human

Direct Speech Reconstruction from Sensorimotor Brain Activity with Optimized Deep Learning Models

TLDR
This paper optimized and validated a decoding approach based on speech reconstruction directly from high-density electrocorticography recordings from sensorimotor cortex during a speech production task and shows that dedicated machine learning optimization of reconstruction models is key for achieving the best reconstruction performance.

Slow Firing Single Units Are Essential for Optimal Decoding of Silent Speech

TLDR
Evidence is provided that slow firing single units are essential for optimal decoding accuracy and can be conditioned in the locked-in participant 5 years after implantation, further supporting their role in decoding.

Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network

TLDR
A compact convolutional network-based architecture whose spatial and temporal filter weights allow for a physiologically plausible interpretation of speech prosthesis based on a compact feature engineering free decoder derived from a small amount of training data is explored.
...

References

SHOWING 1-10 OF 40 REFERENCES

Decoding Inner Speech Using Electrocorticography: Progress and Challenges Toward a Speech Prosthesis

TLDR
The state of the art in decoding inner speech, ranging from early acoustic sound features, to higher order speech units is described, and various challenges commonly encountered when investigating inner speech decoding are emphasized, and potential solutions are proposed in order to get closer to a natural speech assistive device.

Classification of Intended Phoneme Production from Chronic Intracortical Microelectrode Recordings in Speech-Motor Cortex

TLDR
Preliminary results suggest supervised classification techniques are capable of performing large scale multi-class discrimination for attempted speech production and may provide the basis for future communication prostheses.

A Wireless Brain-Machine Interface for Real-Time Speech Synthesis

TLDR
The results support the feasibility of neural prostheses that may have the potential to provide near-conversational synthetic speech output for individuals with severely impaired speech motor control.

Electrocorticographic representations of segmental features in continuous speech

TLDR
This study examined the neural representations of segmental features (place and manner of articulation, and voicing status) in the context of fluent, continuous speech production to provide a new insight into the articulatory and auditory processes underlying speech production in terms of their motor requirements and acoustic correlates.

Speech synthesis from ECoG using densely connected 3D convolutional neural networks.

TLDR
This is the first time that high-quality speech has been reconstructed from neural recordings during speech production using deep neural networks, and uses a densely connected convolutional neural network topology which is well-suited to work with the small amount of data available from each participant.

Real-time classification of auditory sentences using evoked cortical activity in humans.

TLDR
A real-time neural speech recognition (rtNSR) software package was used to classify spoken input from high-resolution electrocorticography signals in real- time, demonstrating the ability of rtNSR to use cortical recordings to perform accuratereal-time speech decoding in a limited vocabulary setting.

Machine translation of cortical activity to text with an encoder–decoder framework

TLDR
It is shown how to decode the electrocorticogram with high accuracy and at natural-speech rates, and how decoding with limited data can be improved with transfer learning, by training certain layers of the network under multiple participants’ data.

NeuroVAD: Real-Time Voice Activity Detection from Non-Invasive Neuromagnetic Signals

TLDR
This study attempted to automatically detect the voice/speech activity directly from the neural signals recorded using magnetoencephalography (MEG), and demonstrated the possibility of real-time VAD direct from the non-invasive neural signals with about 88% accuracy.

Classification of Articulator Movements and Movement Direction from Sensorimotor Cortex Activity

TLDR
It is shown that recordings from small parts of the sensorimotor cortex contain information about different articulator movements which might be used for BCI control, of interest forBCI systems that aim to decode neural activity related to (actual or attempted) movements from a contained cortical area.