Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 4, 2026

Assessment and Communication for People with Disorders of Consciousness

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

Cross-subject decoding of human neural data for speech Brain Computer Interfaces.

Tommaso Boccato¹, Michal Olak², Matteo Ferrante³

¹Tether Evo, Avenida Norte, Calle El Mirador, Edificio Torre Futura Oficina 06, Nivel 11, Colonia Escalon Del Municipio De San Salvador, Crespino, 45030, Italy.

Journal of Neural Engineering

|July 2, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Evidence for compositionality in fMRI visual representations via Brain Algebra.

Communications biology·2025

Same author

Effective Dose Estimation in Computed Tomography by Machine Learning.

Tomography (Ann Arbor, Mich.)·2025

Same author

Retrieving and reconstructing conceptually similar images from fMRI with latent diffusion models and a neuro-inspired brain decoding model.

Journal of neural engineering·2024

Same author

Application of nnU-Net for Automatic Segmentation of Lung Lesions on CT Images and Its Implication for Radiomic Models.

Journal of clinical medicine·2022

This study introduces a novel neural-to-phoneme decoder for brain-to-text systems, achieving high performance across different participants. This breakthrough advances brain-computer interfaces (BCIs) by enabling scalable speech decoding without single-subject training.

Area of Science:

Neuroscience
Computational Linguistics
Biomedical Engineering

Background:

Brain-to-text systems show promise but struggle with cross-subject generalization.
Current models are typically trained on single-participant data, limiting their applicability.

Purpose of the Study:

To develop the first neural-to-phoneme decoder capable of joint training on multiple large-scale intracortical speech datasets.
To investigate and enable cross-subject generalization in brain-to-text systems.

Main Methods:

Jointly trained a hierarchical GRU decoder on two large intracortical speech datasets.
Introduced day- and dataset-specific affine transforms for neural activity alignment.
Incorporated intermediate CTC supervision and feedback connections to address CTC loss assumptions.

Keywords:

BCI Cross-subject brain decoding speech

More Related Videos

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Related Experiment Videos

Last Updated: Jul 4, 2026

Assessment and Communication for People with Disorders of Consciousness

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Main Results:

The decoder matched or surpassed within-subject performance while trained across participants.
The model adapted to new subjects with linear transforms or minimal fine-tuning.
Initial generalization to an independent inner-speech dataset was observed.

Conclusions:

Cross-subject pretraining is a viable strategy for enhancing the scalability of speech brain-computer interfaces (BCIs).
The proposed decoder architecture and alignment techniques facilitate robust cross-subject generalization.