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

Acetylcholinesterase Inhibition Reverses Age-Related Pulmonary Decline and Increases Bronchus-Associated Lymphoid Tissue Formation in Aged Mice.

Biology·2026
Same author

Effect of exercise on Fibroblast Growth Factor 21 levels in healthy males and females.

PloS one·2025
Same author

A Wearable Silent Text Input System Using EMG and Piezoelectric Sensors.

Sensors (Basel, Switzerland)·2025
Same author

Transcranial random noise stimulation shifts time reproduction in opposite directions for ADHD and TD individuals.

Neuropsychologia·2025
Same author

Divergent thinking in groups during cold-water immersion is impaired by cold stress not the cold shock response.

Frontiers in psychology·2025
Same author

Innovative Interstate Academic-Public Health Agency Collaborations for Case Investigations and Outbreak Surge Capacity.

Health security·2025

Related Experiment Video

Updated: Jan 15, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K

Sentence-Level Silent Speech Recognition Using a Wearable EMG/EEG Sensor System with AI-Driven Sensor Fusion and

Nicholas Satterlee1, Xiaowei Zuo1, Kee Moon1

  • 1Department of Mechanical Engineering, San Diego State University, San Diego, CA 92182, USA.

Sensors (Basel, Switzerland)
|October 16, 2025
PubMed
Summary

This study introduces a wearable silent speech recognition system using single-channel EMG and EEG sensors. It achieves 95.25% accuracy for sentence-level recognition, enabling communication without vocalization.

Keywords:
EEGEMGfew-shot learninglanguage modelsensor fusionsilent speech recognition

More Related Videos

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

920

Related Experiment Videos

Last Updated: Jan 15, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

920

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Machine Learning

Background:

  • Silent speech recognition (SSR) traditionally uses non-wearable sensors and struggles with continuous speech.
  • Existing systems often focus on isolated word recognition, limiting real-world application.

Purpose of the Study:

  • To develop a wearable SSR system for accurate sentence-level recognition using minimal biosignal sensors.
  • To integrate electromyography (EMG) and electroencephalography (EEG) for enhanced performance.
  • To enable communication without vocalization through advanced machine learning techniques.

Main Methods:

  • Implemented a wearable system with single-channel EMG and EEG sensors and real-time wireless transmission.
  • Utilized a moving window-based few-shot learning model with a Siamese neural network for continuous signal segmentation and classification.
  • Employed a novel sensor fusion model combining EMG and EEG data.
  • Applied a statistical language model for post-processing error correction.

Main Results:

  • Achieved 95.25% sentence-level recognition accuracy on a dataset of four military command sentences.
  • Demonstrated effective word segmentation and classification from continuous biosignals without pauses.
  • Showcased the efficacy of sensor fusion and language modeling in improving SSR performance.

Conclusions:

  • Validated the feasibility of sentence-level SSR using wearable sensors and limited biosignals.
  • The developed system offers a practical solution for communication without vocalization.
  • Highlights the potential of few-shot learning, sensor fusion, and ML for advanced human-computer interfaces.