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

Statistical methods for retrospective harmonization of longitudinal epidemiological data: a scoping review.

European journal of epidemiology·2026
Same author

Reconstruction of spin structures from topological charge distributions via generative neural network systems.

The Journal of chemical physics·2026
Same author

Everyday Activity Science and Engineering Table Setting Dataset.

Scientific data·2026
Same author

EMBC Special Issue: CogniFuse and Multimodal Deformers: An Extended Study on Benchmarking and Modeling Biosignal Fusion.

IEEE transactions on bio-medical engineering·2026
Same author

Explainable AI Insights Into EEG Classification and Its Alignment to Neural Correlates.

Human brain mapping·2026
Same author

CogniFuse and Multimodal Deformers: A Unified Approach for Benchmarking and Modeling Biosignal Fusion.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Related Experiment Video

Updated: Apr 30, 2026

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

1.8K

Tackling speaking mode varieties in EMG-based speech recognition.

Michael Wand, Matthias Janke, Tanja Schultz

    IEEE Transactions on Bio-Medical Engineering
    |April 25, 2014
    PubMed
    Summary

    This study introduces multimode systems for silent speech recognition using electromyography (EMG). A novel spectral mapping algorithm significantly improves silent speech recognition accuracy by reducing word error rate (WER).

    More Related Videos

    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
    09:09

    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

    Published on: September 27, 2024

    1.1K
    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
    08:15

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

    Published on: March 28, 2025

    1.5K

    Related Experiment Videos

    Last Updated: Apr 30, 2026

    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

    1.8K
    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
    09:09

    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

    Published on: September 27, 2024

    1.1K
    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
    08:15

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

    Published on: March 28, 2025

    1.5K

    Area of Science:

    • Biomedical Engineering
    • Speech Technology
    • Human-Computer Interaction

    Background:

    • Electromyographic (EMG) silent speech recognizers capture articulatory muscle potentials for silent communication.
    • Existing systems face accuracy challenges due to discrepancies between audible and silent speech modes.
    • Establishing a baseline EMG-based continuous speech recognizer is crucial for further investigation.

    Purpose of the Study:

    • To investigate speaking mode variations affecting EMG-based speech recognition accuracy.
    • To introduce and evaluate multimode systems for seamless switching between audible and silent speech.
    • To present a spectral mapping algorithm for improving silent speech recognition performance.

    Main Methods:

    • Developed and implemented multimode systems for audible and silent speech.
    • Investigated various measures to quantify speaking mode differences.
    • Applied a novel spectral mapping algorithm to enhance word error rate (WER) on silent speech data.

    Main Results:

    • The spectral mapping algorithm improved silent speech WER by up to 14.3% relative.
    • Achieved a best average silent speech WER of 34.7%.
    • Achieved a best WER of 16.8% on audibly spoken speech.

    Conclusions:

    • Multimode systems and spectral mapping effectively address speaking mode variations in EMG-based speech recognition.
    • The developed techniques significantly enhance the accuracy of silent speech recognition.
    • This research advances the potential for silent communication using EMG technology.