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

An audio-visual corpus for speech perception and automatic speech recognition.

Martin Cooke1, Jon Barker, Stuart Cunningham

  • 1Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, United Kingdom. m.cooke@dcs.shef.ac.uk

The Journal of the Acoustical Society of America
|December 2, 2006
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

Smart city development and medical service performance: evidence from a province-level panel study in China.

International journal of public health·2026
Same author

Beyond comorbidity: bidirectional association between sleep problems and internet gaming disorder and the mediating role of resilience and emotional problems: a three-wave cohort study among Chinese adolescents.

Journal of psychiatric research·2026
Same author

Peer bullying victimisation and depressive symptoms as serial mediators between attention-deficit/hyperactivity disorder symptoms and internet gaming disorder among Chinese adolescents: A three-wave longitudinal study.

General psychiatry·2026
Same author

Globus pallidus internus versus subthalamic nucleus deep brain stimulation for Meige syndrome: a retrospective study on short- and long-term efficacy.

Journal of neurosurgery·2026
Same author

The First Cadenza Challenge: Perceptual Evaluation of Machine Learning Systems to Improve Audio Quality of Popular Music for Those with Hearing Loss.

Trends in hearing·2026
Same author

Femtosecond lasers in ophthalmology: Mechanisms, clinical breakthroughs, and multidisciplinary frontiers.

Progress in retinal and eye research·2025

A new audio-visual speech corpus supports research in speech perception and automatic speech recognition. This resource features 34 speakers reciting 1000 sentences each, demonstrating high intelligibility.

Area of Science:

  • Linguistics
  • Computer Science
  • Cognitive Science

Background:

  • Speech perception and automatic speech recognition (ASR) research require standardized, high-quality datasets.
  • Existing corpora may lack sufficient diversity or specific features needed for targeted studies.
  • A common material is essential for comparing results across different research groups and methodologies.

Purpose of the Study:

  • To create and provide a novel audio-visual corpus for speech perception and ASR research.
  • To ensure the collected material is suitable for intelligibility testing in various acoustic conditions.
  • To make the annotated corpus readily available for the research community.

Main Methods:

  • Collected high-quality audio and video recordings of 34 distinct talkers.

Related Experiment Videos

  • Each talker recited 1000 simple, syntactically identical sentences.
  • Conducted intelligibility tests using audio signals in quiet and low-noise environments.

    • Main Results:

    • The corpus comprises 34,000 unique sentence recordings (34 speakers x 1000 sentences).
    • Intelligibility tests confirmed the material is easily identifiable in quiet and low stationary noise.
    • The corpus is annotated and accessible online for research purposes.

    Conclusions:

    • The developed audio-visual corpus is a valuable resource for advancing speech perception and ASR.
    • The material's high intelligibility facilitates reliable research outcomes.
    • Web accessibility promotes widespread adoption and collaborative research.