Leigh R. Hochberg

This paper introduces a multi-user transformer-based decoder for intracortical speech BCIs, achieving lower word error rates with less training data than individual models.

Brain2voice 2.0 improves voice synthesis from neural signals, achieving 5.24% word error rate, 8x better than prior methods, enabling real-time intelligible speech for paralyzed individuals.

The paper shows that during typing skill acquisition using a BCI, neural population dynamics in the dorsal premotor cortex become more compact, with left hemisphere showing enhanced firing-rate modulation and generalization.

A paralyzed man with ALS used a long-term intracortical BCI for over two years to communicate, control a computer, and work independently.

This paper tests deep neural ensembles in real-time speech BCIs, showing reduced word error rates and introducing a computationally efficient pseudoensembling method.

The paper shows that premotor cortex uses a compositional neural geometry to plan words by combining phoneme representations, enabling efficient planning of novel sequences.

The paper investigates how motor cortex activity changes during observation of different anthropomorphic effectors, finding increased neural modulation with greater human-likeness of the observed agents.

This study decodes speech mode and loudness from ventral precentral gyrus activity in two participants, achieving high accuracy in predicting speech parameters and developing a closed-loop decoder for expressive speech neuroprostheses.

This paper demonstrates cross-brain transfer learning for intracortical BCIs decoding speech and handwriting, showing improved performance with limited training data and specific decoder design.

This paper improves the interpretability of LFADS models by introducing a per-trial bias, enabling simpler contextual dynamics and better analysis of neural activity in simulated and real data.

This study investigates how preparatory activity in the human motor cortex encodes movement features like direction, curvature, and distance, and demonstrates its use for predictive brain-computer interface control.

This study analyzes neural activity in the precentral gyrus of two spinal cord injury patients to classify hand gestures with 70% accuracy, showing potential for intracortical BCI applications.

This paper decodes intended speech from a person with anarthria and locked-in syndrome using an intracortical brain-computer interface, showing that phonemes, words, and higher-order language units can be decoded above chance.

This paper demonstrates a brain-to-voice neuroprosthesis that synthesizes speech from neural activity, enabling real-time voice modulation with closed-loop feedback.

The paper shows error detection signals in speech motor cortex during neuroprosthesis use, enabling error identification with 86% accuracy and revealing distinct patterns for different error types.

The paper shows that neural activity in human premotor cortex combines finger movements through pseudo-linear summation, with deviations that improve decoding performance.

This paper introduces NoMAD, a method that stabilizes brain-computer interfaces by aligning latent dynamics, achieving stable decoding without supervised recalibration over long periods.

This paper demonstrates that neural activity from ventral motor cortex can enable high-performance cursor control and click for brain-computer interfaces.

The paper introduces EEG-VLM, a method to map neuroanatomical lesions to multidimensional EEG data, finding frontal subcortical white matter lesions correlate with reduced parietal EEG responses.

The paper measures neural signal instability in long-term intracortical recordings to improve brain-computer interface performance through recalibration timing.

The paper studies neural encoding of inner speech in motor cortex and shows it can be decoded, but also identifies a neural dimension that can prevent unintentional decoding of private thoughts.

The paper maps human motor cortex using microelectrode recordings, finding whole-body representations and challenging the traditional motor homunculus model.

This paper develops a flexible intracortical BCI for typing using finger movements, achieving high accuracy and speed in two typing paradigms.

BRAND provides a platform for closed-loop experiments with deep networks, achieving low latency and supporting multiple programming languages.

This paper develops a high-performance brain-computer interface for finger control and quadcopter navigation, achieving fast target acquisition and obstacle course performance.

This paper shows that recurrent neural networks (RNNs) can be adapted for real-time neuroprosthetic control by modifying their training data's temporal structure, enabling better performance than standard linear methods.

The paper introduces FALCON, a benchmark suite for evaluating robustness of iBCI decoders using standardized datasets and evaluation metrics.

This paper demonstrates a high-performance speech neuroprosthesis that achieves low word error rates and high decoding speeds using intracortical recordings from a person with ALS.

This study shows that co-occurring ripple oscillations enhance neuronal interactions between cortical locations in humans by facilitating prediction and co-firing of neurons.

This paper introduces a hidden Markov model for unsupervised recalibration of intracortical brain-computer interfaces, showing improved performance over long-term use.