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

Muscles for Facial Expressions

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...

Facial Feedback Hypothesis

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...

You might also read

Related Articles

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

Sort by

Same author

Optimizing Theta Burst Stimulation Protocols: A Computational Exploration of Novel Alpha-Beta and Alpha-Gamma Frequency Couplings.

Neuroinformatics·2025

Same author

Establishing a methodological framework for evaluating gait symmetry through muscle synergies: A pilot study.

Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology·2025

Same author

Cortical Morphology in Cannabis Use Disorder: Implications for Transcranial Direct Current Stimulation Treatment.

Basic and clinical neuroscience·2024

Same author

Quantifying Human Gait Symmetry During Blindfolded Treadmill Walking.

Motor control·2024

Same author

Modeling of cerebellar transcranial electrical stimulation effects on hand tremor in Parkinson's disease.

Frontiers in aging neuroscience·2023

Same author

Closing the loop between brain and electrical stimulation: towards precision neuromodulation treatments.

Translational psychiatry·2023

Search research articles

Related Experiment Video

Updated: Jul 19, 2026

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

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

Published on: August 9, 2024

Performance enhancement for audio-visual speaker identification using dynamic facial muscle model.

Vahid Asadpour¹, Farzad Towhidkhah, Mohammad Mehdi Homayounpour

¹Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran. asadpour@aut.ac.ir

Medical & Biological Engineering & Computing

|October 13, 2006

Summary

This study introduces a novel audio-visual identification system using dynamic muscle models of lip movements for enhanced security. The system significantly improves speaker recognition accuracy, even in noisy conditions and with identical twins.

More Related Videos

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

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

Published on: September 27, 2024

Related Experiment Videos

Last Updated: Jul 19, 2026

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

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

Published on: August 9, 2024

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

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

Published on: September 27, 2024

Area of Science:

Biometrics and Human Identification
Audio-Visual Signal Processing
Machine Learning for Security

Background:

Biometric identification systems are crucial for security but often rely on single modalities.
Robust audio-visual identification systems, integrating voice and facial cues, remain an underexplored area.
Existing methods lack sufficient robustness against imitation and environmental noise.

Purpose of the Study:

To propose a novel model-based feature extraction method for audio-visual speaker identification.
To leverage physiological characteristics of facial muscles for unique speaker profiling.
To enhance the accuracy and robustness of multimodal identification systems.

Main Methods:

Developed a dynamic lip model extracting intrinsic muscle properties (viscosity, elasticity, mass).
Employed a multistream pseudo-synchronized Hidden Markov Model (HMM) for audio-visual feature fusion.
Utilized noise-robust audio features: Mel-frequency cepstral coefficients (MFCC), spectral subtraction (SS), and J-RASTA-PLP.

Main Results:

The dynamic muscle model significantly improved audio-visual system identification rates from 91% to 98% at 3 dB SNR.
Performance enhancement was validated on identical twins, increasing identification accuracy from 87% to 96%.
The system demonstrated superior robustness against noise and speaker imitation.

Conclusions:

The proposed dynamic muscle model offers a highly effective approach for robust audio-visual speaker identification.
Physiological lip movement features provide unique, imitation-resistant biometric traits.
This method represents a significant advancement in multimodal biometric security systems.