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

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

Chemoenzymatic Syntheses of Tumor-Associated Carbohydrate Antigen Globo-H and Stage-Specific Embryonic Antigen 4.

Advanced synthesis & catalysis·2011

Same author

Identification of tandem mass spectra of mixtures of isomeric peptides.

Journal of proteome research·2010

Same author

Increasing the sensitivity and single-base mismatch selectivity of the molecular beacon using graphene oxide as the "nanoquencher".

Chemistry (Weinheim an der Bergstrasse, Germany)·2010

Same author

Optimal use of silver nitrate and marginal leakage at the sealant-enamel interface using micro-CT.

American journal of dentistry·2010

Same author

The use of hsa-miR-21, hsa-miR-181b and hsa-miR-106a as prognostic indicators of astrocytoma.

European journal of cancer (Oxford, England : 1990)·2010

Same author

Simultaneous elimination of T- and B-cell epitope by structure-based mutagenesis of single Glu80 residue within recombinant staphylokinase.

Acta biochimica et biophysica Sinica·2010

Same journal

Transfer Learning with Simulated and Recorded Data Improves Predictions of Lateral Pinch Thumb-Tip Forces.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Sensing Muscle Deformation for Upper-Limb Prosthetic Control: a Narrative Review.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Entropy-Based Graph Learning Framework for Cross-Subject Detection of Electrical Status Epilepticus During Sleep (ESES).

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Touch-related electrophysiology activity promotes human movements initiation.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Ultrasound-Informed State Estimation of Wrist Tremor Dynamics via Koopman Operator for Personalized Sensory Peripheral Nerve Stimulation.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Motion Intention Recognition and DDPG-Based Adaptive Impedance Control for a Robotic Upper-Limb Exoskeleton.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 3, 2025

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

Decoding Silent Speech Based on High-Density Surface Electromyogram Using Spatiotemporal Neural Network.

Xi Chen, Xu Zhang, Xiang Chen

IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society

|April 11, 2023

Summary

This summary is machine-generated.

This study introduces a new syllable-level decoding method for silent speech recognition using surface electromyogram (sEMG) signals. The novel approach achieved high accuracy in recognizing subvocalized phrases, offering potential for improved communication technologies.

More Related Videos

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Related Experiment Videos

Last Updated: Aug 3, 2025

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

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Area of Science:

Biomedical Engineering
Neuroscience
Artificial Intelligence

Background:

Continuous silent speech recognition (SSR) is crucial for advanced human-computer interfaces.
Decoding speech at a finer granularity (phoneme or syllable level) using surface electromyogram (sEMG) is a key technological challenge.
Existing methods often lack the precision required for real-time, nuanced silent speech interpretation.

Purpose of the Study:

To develop and evaluate a novel syllable-level decoding method for continuous silent speech recognition (SSR).
To utilize spatio-temporal end-to-end neural networks for processing high-density sEMG (HD-sEMG) data.
To enhance the accuracy and efficiency of silent speech decoding for practical applications.

Main Methods:

High-density sEMG (HD-sEMG) data were recorded from facial and laryngeal muscles of 15 subjects.
sEMG signals were converted into a series of feature images for neural network input.
A spatio-temporal end-to-end neural network was employed for feature extraction and syllable-level decoding.
The method was tested on 33 Chinese phrases comprising 82 distinct syllables.

Main Results:

The proposed method achieved a phrase classification accuracy of 97.17 ± 1.53%.
A low character error rate of 3.11 ± 1.46% was obtained, outperforming benchmark methods.
The system demonstrated effective discriminative feature representation from HD-sEMG data.

Conclusions:

The developed syllable-level decoding method offers a promising approach for advancing sEMG-based SSR.
This technology holds significant potential for applications in instant communication and remote control systems.
The spatio-temporal neural network effectively decodes complex muscle activity patterns into speech units.