Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Clinicopathologic characterization of a non-expansile, epilepsy-associated neocortical lesion with BRAF K601E mutation.

Journal of neuropathology and experimental neurology·2026
Same author

Consensus recommendations for clinical functional MRI applied to language mapping.

Aperture neuro·2026
Same author

MAPK-driven glioma progression and reprogramming of the tumor-associated immune response.

Neuro-oncology·2026
Same author

Human intracranial signal stability tracks anatomical accuracy after electrode reimplantation.

Journal of neural engineering·2026
Same author

Cerebrovascular vulnerability and fibrosis in human brain aneurysms.

Nature neuroscience·2026
Same author

Targeted Connectomic Neuromodulation of the Orbitofrontal Cortex To Treat Obsessive-Compulsive Disorder.

medRxiv : the preprint server for health sciences·2026

Related Experiment Video

Updated: Mar 16, 2026

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
05:38

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

3.0K

Neural speech recognition: continuous phoneme decoding using spatiotemporal representations of human cortical

David A Moses1, Nima Mesgarani, Matthew K Leonard

  • 1Department of Neurological Surgery, UC San Francisco, CA, USA. Center for Integrative Neuroscience, UC San Francisco, CA, USA. Graduate Program in Bioengineering, UC Berkeley-UC San Francisco, CA, USA.

Journal of Neural Engineering
|August 4, 2016
PubMed
Summary

Researchers developed a neural speech recognition system using brain activity from the superior temporal gyrus. This system successfully decodes continuous phonemes, advancing speech reconstruction from neural signals.

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

15.3K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

12.4K

Related Experiment Videos

Last Updated: Mar 16, 2026

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
05:38

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

3.0K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

15.3K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

12.4K

Area of Science:

  • Neuroscience
  • Computational Linguistics
  • Biomedical Engineering

Background:

  • The superior temporal gyrus (STG) is crucial for human language processing.
  • Previous speech reconstruction from STG activity lacked modern probabilistic and engineering approaches.

Purpose of the Study:

  • To design and evaluate an initial neural speech recognition (NSR) system.
  • To perform continuous phoneme recognition using electrocorticography (ECoG) data from the STG.
  • To leverage probabilistic frameworks and engineering methodologies from speech recognition.

Main Methods:

  • Utilized high gamma band power of local field potentials from ECoG in the STG.
  • Implemented a Viterbi decoder with linear discriminant analysis for phoneme likelihoods.
  • Incorporated an n-gram phonemic language model for transition probabilities.
  • Employed grid searches for optimizing feature vectors and decoder parameters.

Main Results:

  • Significantly improved system performance using spatiotemporal neural activity representations.
  • Enhanced recognition by including language modeling and Viterbi decoding.
  • Demonstrated successful continuous phoneme recognition with arbitrary vocabulary sizes.

Conclusions:

  • Modeling temporal dynamics of neural responses is vital for stimulus variation analysis.
  • Speech recognition techniques are effective for decoding speech from neural signals.
  • The NSR system shows potential for automatic speech recognition and neural prosthetics.