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 Experiment Videos

Creating speech-synchronized animation.

Scott A King1, Richard E Parent

  • 1Computing and Mathematical Science Department, Texas A&M-Corpus Christi, Center for Instruction-CI 327, 6300 Ocean Dr., Unit 5825, Corpus Christi, TX 78412-5825, USA. sking@sci.tamucc.edu

IEEE Transactions on Visualization and Computer Graphics
|May 5, 2005
PubMed
Summary

This study introduces a muscle-based facial model for realistic animated speech generation. The system efficiently creates high-quality, real-time animated speech from text with low resource needs.

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

Simplified Indoor Localization Using Bluetooth Beacons and Received Signal Strength Fingerprinting with Smartwatch.

Sensors (Basel, Switzerland)·2024
Same author

Pain Management Best Practices from Multispecialty Organizations During the COVID-19 Pandemic and Public Health Crises.

Pain medicine (Malden, Mass.)·2020
Same author

NHE1 inhibition by amiloride- and benzoylguanidine-type compounds. Inhibitor binding loci deduced from chimeras of NHE1 homologues with endogenous differences in inhibitor sensitivity.

The Journal of biological chemistry·2007
Same author

Regulation of the Pleuronectes americanus Na+/H+ exchanger by osmotic shrinkage, beta-adrenergic stimuli, and inhibition of Ser/Thr protein phosphatases.

Cell biochemistry and biophysics·2006
Same author

Membrane transplantation to correct integral membrane protein defects.

Journal of molecular medicine (Berlin, Germany)·2003
Same author

Molecular cloning of NHE1 from winter flounder RBCs: activation by osmotic shrinkage, cAMP, and calyculin A.

American journal of physiology. Cell physiology·2003

Area of Science:

  • Computer graphics
  • Speech synthesis
  • Human-computer interaction

Background:

  • Generating realistic animated speech requires complex facial models.
  • Existing methods often lack the necessary geometric detail for accurate lip and tongue articulation.
  • Integrating speech synchrony with facial expressions remains a challenge.

Purpose of the Study:

  • To develop a novel facial model for animated speech.
  • To enable seamless integration of speech synchrony and facial expressions.
  • To create a system for generating real-time animated speech from unrestricted text.

Main Methods:

  • Input facial geometry is transformed into a muscle-based parametric deformable model.
  • Highly deformable lip, tongue, teeth, gums, and palate models are incorporated.

Related Experiment Videos

  • Hierarchical deformation and a coarticulation model blending visemes as curves are used for animation.
  • Implementation in a text-to-audiovisual-speech system for real-time generation.

    • Main Results:

    • The facial model achieves high geometric complexity for lip shapes and renderings.
    • The system accurately animates speech in real-time from input text.
    • The approach allows for efficient, low-resource production of animated speech.
    • Visemes are dynamically shaped using curves, improving coarticulation modeling.

    Conclusions:

    • The presented facial model effectively supports animated speech generation.
    • The muscle-based parameterization facilitates speech synchrony and expression integration.
    • The text-to-audiovisual-speech system demonstrates efficient and accurate animated speech production.