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

Facial Feedback Hypothesis01:24

Facial Feedback Hypothesis

Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role of...
Muscles for Facial Expressions01:14

Muscles for Facial Expressions

The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
Association Areas of the Cortex01:21

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...

You might also read

Related Articles

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

Sort by
Same author

Integrating stakeholder perspectives in the co-design of medical device software to monitor Parkinson's disease symptoms- A case-study.

MethodsX·2026
Same author

Pipeline to analyse Photoplethysmogram (PPG) Signal Quality.

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

Non-invasive imaging techniques for predicting healing status of diabetic foot ulcers: a ten-year systematic review.

Frontiers in medical technology·2025
Same author

A pilot investigation of muscle conditioning as a tool to study neck proprioception and vestibular reweighting during head to trunk movement.

Scientific reports·2025
Same author

How photoplethysmography can be used to detect major depressive disorder among patients with obstructive sleep apnea during sleep.

Computers in biology and medicine·2025
Same author

Reflexive eye saccadic parameters in Parkinson's disease.

Frontiers in medical technology·2024

Related Experiment Video

Updated: Jul 10, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Unspoken vowel recognition using facial electromyogram.

Sridhar P Arjunan1, Dinesh K Kumar, Wai C Yau

  • 1Sch. of Electr. Eng., RMIT Univ., Melbourne, Vic. 3001, Australia. s3099587@rmit.edu.au

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|October 20, 2007
PubMed
Summary

This study identifies speech using facial muscle activity, not audio. Surface electromyography (SEMG) of facial muscles effectively classified vowels, showing potential for silent, unvoiced commands.

More Related Videos

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans
04:27

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans

Published on: March 15, 2019

Related Experiment Videos

Last Updated: Jul 10, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans
04:27

Using Facial Electromyography to Assess Facial Muscle Reactions to Experienced and Observed Affective Touch in Humans

Published on: March 15, 2019

Area of Science:

  • Biomedical Engineering
  • Speech Recognition Technology
  • Human-Computer Interaction

Background:

  • Traditional speech recognition relies on audio signals, limiting applications in noisy environments or for silent communication.
  • Facial muscle movements (articulatory muscle activity) are intrinsically linked to speech production.
  • Developing non-auditory speech identification methods is crucial for diverse communication needs.

Purpose of the Study:

  • To investigate the feasibility of identifying speech solely through facial muscle activity.
  • To develop and evaluate a technique for measuring and classifying articulatory muscle signals for speech recognition.
  • To assess the robustness of the technique against variations in speaking speed and style.

Main Methods:

  • Utilized surface electromyography (SEMG) to measure electrical activity from four facial muscles.
  • Employed moving root mean square (RMS) to segment speech signals and identify utterance boundaries.
  • Integrated and normalized SEMG RMS signals to represent relative muscle activity for classification.
  • Classified speech signals using a backpropagation neural network.

Main Results:

  • Successfully classified five English vowels into three distinct classes, independent of speaker speed and style.
  • Achieved accurate classification of five vowels into five classes when the model was trained for individual subjects.
  • Demonstrated the technique's sensitivity to subtle facial muscle movements associated with speech.

Conclusions:

  • Facial muscle activity, measured via SEMG, can be effectively used for speech identification without audio input.
  • The developed technique shows promise for applications requiring silent or non-traditional speech command interfaces.
  • Personalized training enhances the accuracy of facial muscle-based speech recognition for specific users.