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

Tongue motion averaging from contour sequences.

Min Li1, Chandra Kambhamettu, Maureen Stone

  • 1Video/Image Modelling and Synthesis Lab, Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716, USA. mli@cis.udel.edu

Clinical Linguistics & Phonetics
|October 7, 2005
PubMed
Summary
This summary is machine-generated.

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

Comparative hyperparameter optimization of object detection models for precision monitoring of cucumber beetles and similar insects on yellow sticky cards.

Scientific reports·2026
Same author

A speech-to-video synthesis approach using spatio-temporal diffusion for vocal tract MRI.

Medical image analysis·2026
Same author

Contrastive Learning Approach for Assessment of Phonological Precision in Patients with Tongue Cancer Using MRI Data.

Interspeech·2024
Same author

Quantifying articulatory variations across phonological environments: An atlas-based approach using dynamic magnetic resonance imaging.

The Journal of the Acoustical Society of America·2024
Same author

Tagged-to-Cine MRI Sequence Synthesis via Light Spatial-Temporal Transformer.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2024
Same author

CHUP1 restricts chloroplast movement and effector-triggered immunity in epidermal cells.

The New phytologist·2024
Same journal

Analysis of an acoustic event in European Portuguese stop-rhotic clusters and implications for phonological acquisition.

Clinical linguistics & phonetics·2026
Same journal

The role of right hemisphere in second language processing: Insights from a case study.

Clinical linguistics & phonetics·2026
Same journal

Audiovisual speech perception in Brazilian Portuguese-speaking children with and without Speech Sound Disorder (SSD).

Clinical linguistics & phonetics·2026
Same journal

Maximising student engagement in learning clinical phonetics and phonology using creative approaches.

Clinical linguistics & phonetics·2026
Same journal

Application of team-based learning to support knowledge acquisition and retention of craniofacial content in a graduate speech-language pathology course: A pilot study.

Clinical linguistics & phonetics·2026
Same journal

Effects of language sampling context on complex syntax production of deaf and hard of hearing children.

Clinical linguistics & phonetics·2026
See all related articles

This study introduces a novel method for creating a superior speech motion representation from multiple ultrasound image sequences. By time-aligning 2D contours and averaging them, researchers can achieve a more accurate depiction of tongue movements during speech.

Area of Science:

  • Medical imaging
  • Speech science
  • Biomechanical modeling

Background:

  • Accurate representation of speech motion is crucial for understanding articulation.
  • Existing methods may not fully capture the dynamic nature of speech due to variations in repetitions.
  • Ultrasound imaging provides a non-invasive window into tongue movements.

Purpose of the Study:

  • To develop a robust method for obtaining the best representation of speech motion from multiple repetitions.
  • To improve the accuracy of speech motion analysis using ultrasound data.
  • To establish a reliable technique for averaging spatio-temporal contours of tongue movements.

Main Methods:

  • Time alignment of 2D spatio-temporal contours from multiple speech repetitions using shape-based Dynamic Programming (DP).

Related Experiment Videos

  • Development of a nonrigid point correspondence recovery method incorporating local stretching and global constraints for Procrustes analysis.
  • Utilizing Procrustes analysis to measure contour similarity and derive the averaged best representation of speech motion.

    • Main Results:

    • Successfully generated an averaged, best representation of speech motion by combining aligned contours from different repetitions.
    • Demonstrated the effectiveness of the developed nonrigid point correspondence method.
    • Validated the proposed method through synthetic data and real-world experiments on tongue motion.

    Conclusions:

    • The proposed method effectively enhances the representation of speech motion from ultrasound data.
    • Averaging time-aligned contours provides a more accurate and stable depiction of articulatory dynamics.
    • This technique offers a valuable tool for speech research and clinical applications.