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

[Automatic voice recognition for radiologic reports. Experiment with a prototype in an operational environment].

A Fusi1, B Vidal

  • 1Centro Ricerca IBM, Roma.

La Radiologia Medica
|March 1, 1991
PubMed
Summary

This study introduces a large vocabulary speech recognition system for Italian, enabling direct voice dictation of medical reports. The prototype achieved over 95% accuracy, proving robust and user-friendly for clinical applications.

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

Time to Reappraise the Antibiotic Treatment for Methicillin-Susceptible Staphylococcus aureus Infective Endocarditis: Data From the Experimental Model.

The Journal of infectious diseases·2025
Same author

Risk scores' performance and their impact on operative decision-making in left-sided endocarditis: a cohort study.

European journal of clinical microbiology & infectious diseases : official publication of the European Society of Clinical Microbiology·2022
Same author

Cemiplimab in advanced cutaneous squamous cell carcinoma: the UK experience from the Named Patient Scheme.

Journal of the European Academy of Dermatology and Venereology : JEADV·2022
Same author

ADENI-UCI study: Analysis of non-income decisions in ICU as a measure of limitation of life support treatments.

Medicina intensiva·2022
Same author

Long-term cardiac assessment in a sample of adolescent-onset anorexia nervosa.

Journal of eating disorders·2022
Same author

Echocardiography and FDG-PET/CT scan in Gram-negative bacteremia and cardiovascular infections.

Current opinion in infectious diseases·2021

Area of Science:

  • Speech Recognition Technology
  • Natural Language Processing
  • Human-Computer Interaction

Context:

  • Development of large vocabulary speech recognition systems for office environments.
  • IBM Rome Science Center and Research Division collaboration on advanced dictation tools.
  • Need for efficient document input methods beyond traditional keyboard use.

Purpose:

  • To develop and test a prototype speech recognition system for Italian natural language.
  • To evaluate the system's suitability for dictating medical reports in a clinical setting.
  • To assess the system's accuracy, robustness, and usability in operational environments.

Summary:

  • A prototype speech recognizer with a 20,000-word Italian vocabulary was developed, running on a PC with specialized hardware.

Related Experiment Videos

  • The system was successfully experimented with by radiologists for direct dictation of medical reports, with immediate on-screen text display and error correction.
  • The system demonstrated robustness, ease of use, and an average recognition rate exceeding 95%.

    • Impact:

    • The system's successful trial in a hospital setting indicates its potential for improving the quantity and quality of medical documentation.
    • Encouraging results provide valuable feedback for future system enhancements in management and efficiency.
    • The technology offers a viable alternative for efficient data entry in specialized professional fields.