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

Improving Translational Accuracy02:07

Improving Translational Accuracy

2.6K
2.6K

You might also read

Related Articles

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

Sort by
Same author

A multilevel longitudinal study of patient-physician communication in later life proactive health behaviors.

Patient education and counseling·2026
Same author

A chronic whole cigarette smoke extract model reveals redox-mitochondrial adaptation in human lung epithelial and organoid models.

Experimental & molecular medicine·2026
Same author

Tumor lysis syndrome in a pediatric patient with Burkitt lymphoma following emergence from general anesthesia: a case report.

Journal of medical case reports·2026
Same author

The Role of Interpersonal Communication Competence in Enhancing Intraoperative Hand-Off Quality.

AORN journal·2026
Same author

Updated pediatric cardiopulmonary resuscitation: a comprehensive review of the 2025 guidelines.

Anesthesia and pain medicine·2026
Same author

Current recommendations for preventing residual neuromuscular blockade.

Anesthesia and pain medicine·2026

Related Experiment Video

Updated: Jul 7, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

589

Improving Medical Speech-to-Text Accuracy using Vision-Language Pre-training Models.

Jaeyoung Huh, Sangjoon Park, Jeong Eun Lee

    IEEE Journal of Biomedical and Health Informatics
    |December 22, 2023
    PubMed
    Summary

    This study introduces a novel Vision Language Pre-training (VLP) method to improve medical Speech-To-Text (STT) accuracy. The VLP approach enhances transcription by using both text and image data, significantly benefiting clinical workflows.

    More Related Videos

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.8K

    Related Experiment Videos

    Last Updated: Jul 7, 2025

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    589
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.8K

    Area of Science:

    • Medical Informatics
    • Artificial Intelligence
    • Natural Language Processing

    Background:

    • Automatic Speech Recognition (ASR) and Speech-To-Text (STT) technologies facilitate human-machine interaction.
    • Medical STT can reduce clinician workload but faces challenges due to limited domain-specific data.
    • Existing general STT systems require domain adaptation for specialized fields like medicine.

    Purpose of the Study:

    • To propose a novel text correction method for medical domain STT.
    • To leverage Vision Language Pre-training (VLP) for enhancing STT accuracy in clinical settings.
    • To demonstrate the superiority of multi-modal understanding over single-modal approaches in medical STT.

    Main Methods:

    • Developed a medical-domain text correction method using Vision Language Pre-training (VLP).
    • VLP model integrates textual and visual information for context-aware text correction.
    • Evaluated the proposed method on medical speech transcription tasks.

    Main Results:

    • The proposed VLP-based method significantly improved STT performance in the medical domain.
    • Quantitative and clinical improvements in transcription accuracy were observed.
    • Multi-modal understanding (image and text) outperformed text-only approaches.

    Conclusions:

    • Vision Language Pre-training offers a powerful solution for improving medical STT accuracy.
    • Integrating visual context with text enhances the robustness of STT systems in specialized domains.
    • This approach has the potential to streamline clinical documentation and reduce transcription errors.