Biology subjects

Hochberg, L. R.

Publications and source records attributed to Hochberg, L. R..

At least 19 recordsLinked to original sources

bioRxiv2026

A generalizable speech neuroprosthesis

Intracortical brain-computer interfaces (BCIs) can restore communication to people with vocal tract paralysis by decoding cortical activity during attempted speech into text. State-of-the-art systems pairing neural-to-phoneme decoders with phoneme-to-word language models have achieved word error rates (WERs) as low as 1%, but only after collecting thousands of sentences of training data. Shortening the data collection process would facilitate scaling this new technology by reducing the time from device implant to high-accuracy communication. Here we introduce a transformer-based decoder model trained jointly across six intracortical speech BCI participants. For every participant -- regardless of sex, disease etiology, or attempted speaking strategy -- a multi-user model decoded speech more accurately (over 50% lower relative WER on average) than models trained on individual users data. Notably, the multi-user model could be finetuned on fewer than 200 sentences from a held-out user to achieve a WER below 7%. These results reveal how to pool intracortical data across people to yield more accurate, generalizable, and rapidly-deployable decoding models.

bioengineering↗

bioRxiv2026

Brain2voice 2.0: High-performance voice synthesis brain-computer interface

Brain-computer interfaces (BCIs) offer a promising solution to speech loss due to neurological injury by decoding intended speech directly from brain activity. While recent BCIs have restored high-accuracy text-based communication, they fail to provide instantaneous voice output essential for the natural flow of conversation. Brain-to-voice BCIs address this gap by decoding voice directly from neural signals. However, even the state-of-the-art (SOTA) BCI-synthesized voice is not yet intelligible enough for real-world adoption. We introduce brain2voice 2.0, a new multimodal Transformer-based BCI decoder architecture capable of synthesizing highly intelligible voice from intracortical neural signals in real-time. Brain2voice 2.0 is trained on continuous and custom-tokenized acoustic targets and phoneme targets, leveraging their complementary speech information. We use self-supervised and adversarial training objectives that enhance acoustic feature quality and improve synthesis intelligibility. At each 10 ms timestep, the model causally outputs continuous and tokenized acoustic features for real-time voice synthesis as well as time-aligned phoneme predictions (raw phoneme error rate: 7%, comparable to the latest brain-to-text models). We evaluated this new approach on our prior intracortical brain-to-voice benchmark dataset (Wairagkar et al. 2025). Naive human listeners transcribed brain2voice 2.0 synthesized voice with a word error rate of 5.24%--an 8x improvement in intelligibility over previous SOTA results (43.75%). Brain2voice 2.0 demonstrates that highly intelligible real-time voice synthesis from neural signals is achievable, for the first time crossing the intelligibility threshold necessary for clinically viable brain-to-voice BCIs for people with paralysis.

neuroscience↗

bioRxiv2026

Learning-related population dynamics in right and left dorsal premotor cortex during typing skill acquisition

Advances in intracortical brain-computer interface (BCI) technology have enabled increasingly sophisticated communication paradigms, including for decoding intended speech and touch typing. However, the methods by which intracortical neural population dynamics are engaged during practice-related skill acquisition in humans remain poorly understood. Here, we examined learning-related changes in neural activity during motor skill acquisition in a right-handed BCI clinical trial participant with tetraplegia, with intracortical microelectrode arrays placed in the bilateral dorsal precentral gyri (Brodmann area 6d), who learned how to type using a BCI-enabled typing interface. While decoder performance remained stable across sessions, typing speed improved with practice, indicating practice-related skill acquisition. Over weeks, low-dimensional neural population activity became progressively more compact, and this compaction was strongly associated with faster typing, independent of decoder accuracy. Although this compaction was observed bilaterally in 6d, firing-rate modulation and cross-session generalization were selectively enhanced in left 6d. Moreover, neural population changes across sessions were largely accounted for by canonical correlation analysis in right 6d, but only partially accounted for in left 6d. Together, these findings demonstrate that human intracortical neuro-motor skill acquisition related to intended typing engages shared bilateral population-level dynamics, with additional learning-related changes selectively expressed in dominant dorsal premotor cortex.

neuroscience↗

bioRxiv2026

Neural decoding of speech using deep neural ensembles

Speech brain-computer interfaces (BCIs) can restore rapid communication to people with paralysis, but decoding errors still limit performance. In recent brain-to-text decoding competitions, deep ensemble methods, which combine predictions from multiple independently trained decoders, have delivered striking accuracy improvements and account for the largest gains over baseline approaches. However, these methods have not previously been tested in real-time, require substantial computational resources, and their performance under various clinically relevant constraints remains poorly understood. Here, we present the first closed-loop test of deep ensembles in a participant with bilateral intracortical microelectrode arrays, demonstrating a reduction in word error rate from 33.7% to 26.0% on a large-vocabulary task. Using additional data from three participants, we then assess how these gains depend on baseline error rate, training dataset size, and ensemble size, including the resource-accuracy tradeoffs most relevant for real-world deployment. Finally, we introduce a computationally efficient pseudoensembling approach based on test-time augmentation that improves decoding accuracy while requiring only a single base decoder, greatly reducing the computational burden of ensembling. Together, these results show that the benefits of deep ensembling can be realized in real time and under practical resource constraints, bringing speech BCIs closer to broader clinical adoption.

neuroscience↗

bioRxiv2026

Premotor cortex uses a compositional neural geometry to plan words

Speech requires precise serial ordering of words and phonemes into novel combinations. To accomplish this, the brain is believed to flexibly prepare utterances before producing them, even allowing pronunciation of never-before spoken words. To discover how neural populations achieve this, intracortical activity from premotor cortex was recorded while two speech neuroprosthesis pilot clinical trial participants attempted to speak factorially-balanced phoneme sequences. During preparation, activity encoded not only the next-phoneme, but multiple upcoming phoneme positions spanning whole words. We found that word-level plans were formed by compositionally combining phoneme representations, a mechanism that may enable efficient planning of novel sequences. When utterances contained more than one word, premotor cortex activity was largely limited to the first word, suggesting that articulatory planning is segmented by higher-order features. Together, these results reveal a compositional, hierarchically-segemented planning geometry, potentially a universal neural strategy for sequence organization across higher levels of language.

neuroscience↗

bioRxiv2026

Observation-Related Activity in Human Motor Cortex Increases with Effector Anthropomorphicity

Neurons in motor cortex can be engaged not only in motor execution but also during observation of movements performed by other anthropomorphic agents (i.e. humans or monkeys). However, it is unknown how motor cortical neurons respond during observation of the range of assistive or prosthetic devices controlled by people using intracortical brain-computer interfaces (iBCIs). We recorded single-unit activity in the precentral gyrus while iBCI users viewed grasp-like movements performed by a spectrum of virtual effectors that included human, robotic, and hand-like dot stimuli. We found a relationship between neural modulation and effector anthropomorphicity (i.e. human-likeness) that existed on an ensemble-wide and individual neuron level, suggesting that human motor cortex activity incrementally increases in response to the visually observed agents human-likeness. Both solicited and spontaneous feedback from the participant indicated a relationship between neural activity and subjective assessments of anthropomorphicity, revealing a powerful contribution of context on observation-induced activity in motor cortex. The activity of motor cortex remained similar during attempted hand movements while different effectors were being observed, suggesting that intuitive external device control via iBCIs may not be overtly affected by the anthropomorphicity of the effector. SIGNIFICANCE STATEMENTThe tendency for neurons in motor cortex to respond during movement observation has been proposed to underlie cognitive processes from motor learning and language development to empathy and theory of mind. Understanding how the motor cortex is engaged during observation of abstract and anthropomorphic agents informs our understanding of these processes and may guide development of neural prostheses which harness the activity of motor cortical neurons to restore lost neurologic function. Here we provide unique neuron-level evidence that human motor cortex activity is gradually modulated by how human-like an observed agent appears and moves. This finding advances our interpretation of "mirror" activity in the brain and could help guide the design of brain-controlled prostheses used by people with tetraplegia.

neuroscience↗

bioRxiv2026

Cross-brain transfer of high-performance intracortical speech and handwriting BCIs

Intracortical brain-computer interfaces (BCIs) that decode complex movements, such as handwriting and speech, can require substantial training data to achieve high performance. We investigated whether leveraging the neural activity recordings of previous users could reduce this initial data collection burden for new BCI users (an approach we call "cross-brain transfer"). Using intracortical recordings from five BrainGate2 clinical trial participants, we tested cross-brain transfer for both speech and handwriting neural decoders trained and evaluated on general, unconstrained corpora of spoken and written English. We found that cross-brain transfer improved decoding performance when training data from the target user was limited (< 200 sentences), and that dataset-specific input layers to the decoder were critical for combining data across users. Without trainable input layers, transfer failed and performed worse than training from scratch on target user data only. Finally, we measured the effectiveness of cross-brain transfer relative to training with (1) more data from the same user and (2) more electrode-permuted data from the same user, which simulates sampling from another brain with identical neural latent structure. In some cases (T16 speech, T12 handwriting), cross-brain transfer appeared as effective as additional permuted data from the same user, while in others (T12 speech, T15 speech) electrode-permuted data was more beneficial. Our results successfully demonstrate and characterize cross-brain transfer learning between multiple intracortical BCI users, for both speech and handwriting, using a general open-ended dataset not restricted to small sets of words or phrases. This work highlights a promising path towards addressing a key barrier to the clinical translation of BCIs, while clarifying when cross-brain transfer may be most beneficial and the decoder design choices needed to realize those gains.

neuroscience↗

bioRxiv2025

Improved interpretability in LFADS models using a learned, context-dependent per-trial bias

The computation-through-dynamics perspective argues that biological neural circuits process information via the continuous evolution of their internal states. Inspired by this perspective, Latent Factor Activity using Dynamical systems (LFADS, [1]) identifies a generative model consistent with the neural activity recordings. LFADS models neural dynamics with a recurrent neural network (RNN) generator, which results in excellent fit to the data. However, it has been difficult to understand the dynamics of the LFADS generator. In this work, we show that this poor interpretability arises in part because the generator implements complex, multi-stable dynamics. We introduce a simple modification to LFADS that ameliorates issues with interpretability by providing an inferred per-trial bias (modeled as a constant input) to the RNN generator, enabling it to contextually adapt a simpler dynamical system to individual trials. In both simulated neural recordings from pendulum oscillations and real recordings during arm movements in nonhuman primates, we observed that the standard LFADS learned complex, multi-stable dynamics, whereas the modified LFADS learned easier-to-understand contextual dynamics. This enabled direct analysis of the generator, which reproduced at a single-trial level previous results shown only through more complex analyses at the trial average. Finally, we applied the per-trial inferred bias LFADS model to human intracortical brain computer interface recordings during attempted finger movements and speech. We show that modifying neural dynamics using linear operations of the per-trial bias addresses non-stationarity and identifies the extent of behavioral variability, problems known to plague BCI. We call our modification to LFADS as "contextual LFADS".

neuroscience↗

bioRxiv2025

Preparatory encoding of diverse features of intended movement in the human motor cortex

Over the course of a voluntary movement, motor cortical activity exhibits a transition from preparation to execution, with markedly different activity across these phases. Preparatory activity in particular might be used to improve brain-computer interfaces (BCIs) that harness brain activity to control external assistive devices, for example by anticipating a users intended movement trajectory for quick and fluid performance. However, to leverage preparatory activity for clinical BCIs, we must first understand which features of upcoming movements are encoded by preparatory activity in humans. In this work, we collected intracortical recordings from 3 research participants in the BrainGate2 clinical trial to investigate whether diverse features of movement, such as direction, curvature, and distance, are encoded by preparatory activity in the human motor cortex. We first show that preparatory activity is tuned to the direction of upcoming movements, and this tuning is largely preserved across movements with different effectors. Further investigation demonstrated this preparatory activity is also informative of initial and endpoint directions of curved movement trajectories, and encodes movement distance and speed independently. Finally, we present an online control paradigm that leverages preparatory activity to predict movements towards intended directions in advance, yielding rapid, self-paced control of a computer cursor by human participants. Altogether, these results demonstrate that preparatory activity in the human motor cortex encodes rich features of upcoming movement, highlighting its potential use for high performance brain-computer interface applications.

neuroscience↗

bioRxiv2025

Decoding intended speech with an intracortical brain-computer interface in a person with longstanding anarthria and locked-in syndrome

Intracortical brain-computer interfaces (iBCIs) for decoding intended speech have provided individuals with ALS and severe dysarthria an intuitive method for high-throughput communication. These advances have been demonstrated in individuals who are still able to vocalize and move speech articulators. Here, we decoded intended speech from an individual with longstanding anarthria, locked-in syndrome, and ventilator dependence due to advanced symptoms of ALS. We found that phonemes, words, and higher-order language units could be decoded well above chance. While sentence decoding accuracy was below that of demonstrations in participants with dysarthria, we are able to attain an extensive characterization of the neural signals underlying speech in a person with locked-in syndrome and through our results identify several directions for future improvement. These include closed-loop speech imagery training and decoding linguistic (rather than phonemic) units from neural signals in middle precentral gyrus. Overall, these results demonstrate that speech decoding from motor cortex may be feasible in people with anarthria and ventilator dependence. For individuals with longstanding anarthria, a purely phoneme-based decoding approach may lack the accuracy necessary to support independent use as a primary means of communication; however, additional linguistic information embedded within neural signals may provide a route to augment the performance of speech decoders.

neuroscience↗

bioRxiv2025

Long-term independent use of an intracortical brain-computer interface for speech and cursor control

Brain-computer interfaces (BCIs) can provide naturalistic communication and digital access to people with severe paralysis by decoding neural activity associated with attempted speech and movement. Recent work has demonstrated highly accurate intracortical BCIs for speech and cursor control, but two critical capabilities needed for practical viability were unmet: independent at-home operation without researcher assistance, and reliable long-term performance supporting accurate speech and cursor decoding. Here, we demonstrate the independent and near-daily use of a multimodal BCI with novel brain-to-text speech and computer cursor decoders by a man with paralysis and severe dysarthria due to amyotrophic lateral sclerosis (ALS). Over nearly two years, the participant used the BCI for more than 3,800 cumulative hours to maintain rich interpersonal communication with his family and friends, independently control his personal computer, and sustain full-time employment - despite being paralyzed. He communicated 183,060 sentences - totaling 1,960,163 words - at an average rate of 56.1 words per minute. He labeled 92.3% of sentences as being decoded at least mostly correctly. In formal quantifications of performance where he was asked to say words presented on a screen, attempted speech was consistently decoded with over 99% word accuracy (125,000 word vocabulary). The participant also used the speech BCI as keyboard input and the cursor BCI as mouse input to control his personal computer, enabling him to send text messages, emails, and to browse the internet. These results demonstrate that intracortical BCIs have the potential to support independent use in the home, marking a critical step toward practical assistive technology for people with severe motor impairment.

neuroscience↗

bioRxiv2025

Error encoding in human speech motor cortex

Humans monitor their actions, including detecting errors during speech production. This self-monitoring capability also enables speech neuroprosthesis users to recognize mistakes in decoded output upon receiving visual or auditory feedback. However, it remains unknown whether neural activity related to error detection is present in the speech motor cortex. In this study, we demonstrate the existence of neural error signals in speech motor cortex firing rates during intracortical brain-to-text speech neuroprosthesis use. This activity could be decoded to enable the neuroprosthesis to identify its own errors with up to 86% accuracy. Additionally, we observed distinct neural patterns associated with specific types of mistakes, such as phonemic or semantic differences between the persons intended and displayed words. These findings reveal how feedback errors are represented within the speech motor cortex, and suggest strategies for leveraging these additional cognitive signals to improve neuroprostheses.

neuroscience↗

bioRxiv2025

Encoding of speech modes and loudness in ventral precentral gyrus

The ability to vary the mode and loudness of speech is an important part of the expressive range of human vocal communication. However, the encoding of these behaviors in the ventral precentral gyrus (vPCG) has not been studied at the resolution of neuronal firing rates. We investigated this in two participants who had intracortical microelectrode arrays implanted in their vPCG as part of a speech neuroprosthesis clinical trial. Neuronal firing rates modulated strongly in vPCG as a function of attempted mimed, whispered, normal or loud speech. At the neural ensemble level, mode/loudness and phonemic content were encoded in distinct neural subspaces. Attempted mode/loudness could be decoded from vPCG with an accuracy of 94% and 89% for two participants respectively, and corresponding neural preparatory activity could be detected hundreds of milliseconds before speech onset. We then developed a closed-loop loudness decoder that achieved 94% online accuracy in modulating a brain-to-text speech neuroprosthesis output based on attempted loudness. These findings demonstrate the feasibility of decoding mode and loudness from vPCG, paving the way for speech neuroprostheses capable of synthesizing more expressive speech.

neuroscience↗

bioRxiv2024

EEG-VLM Toolbox: Extending voxel-based lesion mapping to multi-dimensional EEG data

Focal brain lesions (such as with stroke) cause functional changes in local and distributed neural systems. While there is a long history of post-stroke neurophysiological assessment using electroencephalography (EEG), the observed neurophysiological changes have rarely been related to specific lesion locations. Therefore, the relationships between anatomical injury and physiological changes after stroke remain unclear. Voxel-based lesion symptom mapping (VLSM) is a tool for statistically relating stroke lesion locations to "symptoms", but current VLSM methods are restricted to symptoms that can be defined by a single value. Therefore, current VLSM techniques are unable to map the relationships between anatomical injury and multidimensional neurophysiological data such as EEG, which contains rich spatio-temporal information across different channels and frequency bands. Here we present a novel algorithm, EEG Voxel-based Lesion Mapping (EEG-VLM), that produces the set of significant relationships between precise neuroanatomical injury locations and neurophysiology (defined by a cluster of adjacent EEG channels and frequency bands). Further, the algorithm provides statistical analyses to define the overall significance of each neural structure-function relationship by correcting for multiple comparisons using a permutation test. Applying EEG-VLM to a dataset of recordings from chronic stroke patients performing a cued upper extremity movement task, we found that subjects with lesions in frontal subcortical white matter have reduced ipsilesional parietal cue-evoked EEG responses. These results are consistent with damage to a frontal-parietal network that has been associated with impairments in attention. EEG-VLM is a novel and unbiased method for relating neurophysiologic changes after stroke with neuroanatomic lesions. In the context of focal brain lesions associated with neurological impairments, we propose that this method will enable improved mechanistic understanding, facilitate biomarker development, and guide neurorehabilitation strategies.

neuroscience↗

bioRxiv2024

Representation of Verbal Thought in Motor Cortex and Implications for Speech Neuroprostheses

Speech brain-computer interfaces show great promise in restoring communication for people who can no longer speak1-3, but have also raised privacy concerns regarding their potential to decode private verbal thought4-6. Using multi-unit recordings in three participants with dysarthria, we studied the representation of inner speech in the motor cortex. We found a robust neural encoding of inner speech, such that individual words and continuously imagined sentences could be decoded in real-time This neural representation was highly correlated with overt and perceived speech. We investigated the possibility of "eavesdropping" on private verbal thought, and demonstrated that verbal memory can be decoded during a non-speech task. Nevertheless, we found a neural "overtness" dimension that can help to avoid any unintentional decoding. Together, these results demonstrate the strong representation of verbal thought in the motor cortex, and highlight important design considerations and risks that must be addressed as speech neuroprostheses become more widespread.

neuroscience↗

bioRxiv2024

A mosaic of whole-body representations in human motor cortex

Understanding how the body is represented in motor cortex is key to understanding how the brain controls movement. The precentral gyrus (PCG) has long been thought to contain largely distinct regions for the arm, leg and face (represented by the "motor homunculus"). However, mounting evidence has begun to reveal a more intermixed, interrelated and broadly tuned motor map. Here, we revisit the motor homunculus using microelectrode array recordings from 20 arrays that broadly sample PCG across 8 individuals, creating a comprehensive map of human motor cortex at single neuron resolution. We found whole-body representations throughout all sampled points of PCG, contradicting traditional leg/arm/face boundaries. We also found two speech-preferential areas with a broadly tuned, orofacial-dominant area in between them, previously unaccounted for by the homunculus. Throughout PCG, movement representations of the four limbs were interlinked, with homologous movements of different limbs (e.g., toe curl and hand close) having correlated representations. Our findings indicate that, while the classic homunculus aligns with each areas preferred body region at a coarse level, at a finer scale, PCG may be better described as a mosaic of functional zones, each with its own whole-body representation.

neuroscience↗

bioRxiv2024

Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark

Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded with an implanted device. While this activity yields high-performance decoding over short timescales, neural data are often nonstationary, which can lead to decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, which requires the arduous collection of new neural and behavioral data. Aiming to reduce this burden, several approaches have been developed that either limit recalibration data requirements (few-shot approaches) or eliminate explicit recalibration entirely (zero-shot approaches). However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner. Here we introduce the FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) to standardize evaluation of iBCI robustness. FALCON curates five datasets of neural and behavioral data that span movement and communication tasks to focus on behaviors of interest to modern-day iBCIs. Each dataset includes calibration data, optional few-shot recalibration data, and private evaluation data. We implement a flexible evaluation platform which only requires user-submitted code to return behavioral predictions on unseen data. We also seed the benchmark by applying baseline methods spanning several classes of possible approaches. FALCON aims to provide rigorous selection criteria for robust iBCI decoders, easing their translation to real-world devices. https://snel-repo.github.io/falcon/

neuroscience↗

bioRxiv2024

Gesture encoding in human left precentral gyrus neuronal ensembles

Understanding the cortical activity patterns driving dexterous upper limb motion has the potential to benefit a broad clinical population living with limited mobility through the development of novel brain-computer interface (BCI) technology. The present study examines the activity of ensembles of motor cortical neurons recorded using microelectrode arrays in the dominant hemisphere of two BrainGate clinical trial participants with cervical spinal cord injury as they attempted to perform a set of 48 different hand gestures. Although each participant displayed a unique organization of their respective neural latent spaces, it was possible to achieve classification accuracies of [~]70% for all 48 gestures (and [~]90% for sets of 10). Our results show that single unit ensemble activity recorded in a single hemisphere of human precentral gyrus has the potential to generate a wide range of gesture-related signals across both hands, providing an intuitive and diverse set of potential command signals for intracortical BCI use.

neuroscience↗