A5026877956- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Muscle activation and electromyography studies
- Advanced Memory and Neural Computing
- Gaze Tracking and Assistive Technology
- Neural dynamics and brain function
- Speech Recognition and Synthesis
- Action Observation and Synchronization
- Blind Source Separation Techniques
- Assistive Technology in Communication and Mobility
Stanford University
2018-2025
Howard Hughes Medical Institute
2020-2025
Speech brain-computer interfaces (BCIs) have the potential to restore rapid communication people with paralysis by decoding neural activity evoked attempted speech into text
Brain-computer interfaces have so far focused largely on enabling the control of a single effector, for example computer cursor or robotic arm. Restoring multi-effector motion could unlock greater functionality people with paralysis (e.g., bimanual movement). However, it may prove challenging to decode simultaneous multiple effectors, as we recently found that compositional neural code links movements across all limbs and tuning changes nonlinearly during dual-effector motion. Here,...
Abstract People with paralysis express unmet needs for peer support, leisure activities and sporting activities. Many within the general population rely on social media massively multiplayer video games to address these needs. We developed a high-performance, finger-based brain–computer-interface system allowing continuous control of three independent finger groups, which thumb can be controlled in two dimensions, yielding total four degrees freedom. The was tested human research participant...
Speaking is a sensorimotor behavior whose neural basis difficult to study with single neuron resolution due the scarcity of human intracortical measurements. We used electrode arrays record from motor cortex ‘hand knob’ in two people tetraplegia, an area not previously implicated speech. Neurons modulated during speaking and non-speaking movements tongue, lips, jaw. This challenges whether conventional model ‘motor homunculus’ division by major body regions extends single-neuron scale....
Objective. To evaluate the potential of intracortical electrode array signals for brain-computer interfaces (BCIs) to restore lost speech, we measured performance decoders trained discriminate a comprehensive basis set 39 English phonemes and synthesize speech sounds via neural pattern matching method. We decoded correlates spoken-out-loud words in 'hand knob' area precentral gyrus, step toward eventual goal decoding attempted from ventral areas patients who are unable speak. Approach....
Abstract Speech brain-computer interfaces (BCIs) have the potential to restore rapid communication people with paralysis by decoding neural activity evoked attempted speaking movements into text 1,2 or sound 3,4 . Early demonstrations, while promising, not yet achieved accuracies high enough for of unconstrainted sentences from a large vocabulary 1–7 Here, we demonstrate first speech-to-text BCI that records spiking intracortical microelectrode arrays. Enabled these high-resolution...
People with paralysis express unmet needs for peer support, leisure activities, and sporting activities. Many within the general population rely on social media massively multiplayer video games to address these needs. We developed a high-performance finger brain-computer-interface system allowing continuous control of 3 independent groups 2D thumb movements. The was tested in human research participant over sequential trials requiring fingers reach hold targets, an average acquisition rate...
Abstract Advances in deep learning have given rise to neural network models of the relationship between movement and brain activity that appear far outperform prior approaches. Brain-computer interfaces (BCIs) enable people with paralysis control external devices, such as robotic arms or computer cursors, might stand benefit greatly from these advances. We tested recurrent networks (RNNs) on a challenging nonlinear BCI problem: decoding continuous bimanual two cursors. Surprisingly, we found...
Abstract Intracortical brain-computer interfaces (iBCIs) require frequent recalibration to maintain robust performance due changes in neural activity that accumulate over time. Compensating for this nonstationarity would enable consistently high without the need supervised periods, where users cannot engage free use of their device. Here we introduce a hidden Markov model (HMM) infer what targets are moving toward during iBCI use. We then retrain system using these inferred targets, enabling...
Keyboard typing with finger movements is a versatile digital interface for users diverse skills, needs, and preferences. Currently, such an does not exist people paralysis. We developed intracortical brain-computer (BCI) attempted flexion/extension of three groups on the right hand, or both hands, demonstrated its flexibility in two dominant paradigms. The first paradigm "point-and-click" typing, where BCI user selects one key at time using continuous real-time control, allowing selection...
Speech-related neural modulation was recently reported in 'arm/hand' area of human dorsal motor cortex that is used as a signal source for intracortical brain-computer interfaces (iBCIs). This raises the concern speech-related might deleteriously affect decoding arm movement intentions, instance by affecting velocity command outputs. study sought to clarify whether or not speaking would interfere with ongoing iBCI use. A participant BrainGate2 clinical trial an control computer cursor; spoke...
Abstract How does the motor cortex combine simple movements (such as single finger flexion/extension) into complex hand gestures or playing piano)? Motor cortical activity was recorded using intracortical multi-electrode arrays in two people with tetraplegia they attempted single, pairwise and higher order movements. Neural for simultaneous largely aligned linear summation of corresponding movement activities, violations. First, neural normalized, preventing a large magnitude an increasing...
Summary Brain-computer interfaces (BCIs) can restore communication to people who have lost the ability move or speak. To date, a major focus of BCI research has been on restoring gross motor skills, such as reaching and grasping 1–5 point-and-click typing with 2D computer cursor 6,7 . However, rapid sequences highly dexterous behaviors, handwriting touch typing, might enable faster rates. Here, we demonstrate an intracortical that decode imagined movements from neural activity in cortex...
Intracortical brain computer interfaces (iBCIs) decode neural activity from the cortex and enable motor communication prostheses, such as cursor control, handwriting speech, for people with paralysis. This paper introduces a new iBCI prosthesis using 3D keyboard interface typing continuous, closed loop movement of multiple fingers. A participant-specific BCI prototype was developed BrainGate2 clinical trial participant (T5) recordings hand-knob area left premotor cortex. We assessed relative...
Intracortical brain-computer interfaces (iBCIs) have shown promise for restoring rapid communication to people with neurological disorders such as amyotrophic lateral sclerosis (ALS). However, maintain high performance over time, iBCIs typically need frequent recalibration combat changes in the neural recordings that accrue days. This requires iBCI users stop using and engage supervised data collection, making system hard use. In this paper, we propose a method enables self-recalibration of...
Abstract Decades after the motor homunculus was first proposed, it is still unknown how different body parts are intermixed and interrelated in human cortex at single-neuron resolution. Using microelectrode arrays, we studied face, head, arm leg movements on both sides of represented hand knob area precentral gyrus people with tetraplegia. Contrary to traditional somatotopy, found strong representation all movements. Probing further, that ipsilateral contralateral movements, homologous (e.g....
Abstract Objective To evaluate the potential of intracortical electrode array signals for brain-computer interfaces (BCIs) to restore lost speech, we measured performance classifiers trained discriminate a comprehensive basis set speech: 39 English phonemes. We classified neural correlates spoken-out-loud words in “hand knob” area precentral gyrus, which view as step towards eventual goal decoding attempted speech from ventral areas patients who are unable speak. Approach Neural and audio...
ABSTRACT Speaking is a sensorimotor behavior whose neural basis difficult to study at the resolution of single neurons due scarcity human intracortical measurements and lack animal models. We recorded from electrode arrays in ‘hand knob’ area motor cortex people with tetraplegia. Neurons this area, which have not previously been implicated speech, modulated during speaking non-speaking movement tongue, lips, jaw. This challenges whether conventional model ‘motor homunculus’ division by major...
Understanding the cortical activity patterns driving dexterous upper limb motion has potential to benefit a broad clinical population living with limited mobility through development of novel brain-computer interface (BCI) technology. The present study examines ensembles motor neurons recorded using microelectrode arrays in dominant hemisphere two BrainGate trial participants cervical spinal cord injury as they attempted perform set 48 different hand gestures. Although each participant...
Abstract Speech brain-computer interfaces show great promise in restoring communication for people who can no longer speak 1–3 , but have also raised privacy concerns regarding their potential to decode private verbal thought 4–6 . Using multi-unit recordings three participants with dysarthria, we studied the representation of inner speech motor cortex. We found a robust neural encoding speech, such that individual words and continuously imagined sentences could be decoded real-time This was...
Brain–computer interfaces (BCIs) can restore com-munication to people who have lost the ability move or speak. So far, a major focus of BCI research has been on restoring gross motor skills, such as reaching and grasping1–5 point-and-click typing with computer cursor. However, rapid sequences highly dexterous behaviours, handwriting touch typing, might enable faster rates communication. Here we developed an intracortical that decodes attempted movements from neural activity in cortex...