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

Statistical clustering procedures applied to low-cost speech recognition.

R I Damper, S L MacDonald

    Journal of Biomedical Engineering
    |October 1, 1984
    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

    Drug modification of LPS-stimulated human monocyte-derived dendritic cells.

    British journal of biomedical science·2012
    Same author

    Customizing kernel functions for SVM-based hyperspectral image classification.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
    Same author

    MBL really binds to healthy human cells!

    Scandinavian journal of immunology·2007
    Same author

    Association between mannan-binding lectin and impaired lung function in cystic fibrosis may be age-dependent.

    Clinical and experimental immunology·2006
    Same author

    Human serum amyloid P component binds to peripheral blood monocytes.

    Scandinavian journal of immunology·2006
    Same author

    Detection of an autologous ligand for mannan-binding lectin on human B lymphocytes.

    Scandinavian journal of immunology·2005
    Same journal

    Comparative study of the function of the Abiomed polyurethane heart valve for use in left ventricular assist devices.

    Journal of biomedical engineering·1993
    Same journal

    AZTDIS--a two-phase real-time ECG data compressor.

    Journal of biomedical engineering·1993
    Same journal

    Validation of an automated method of three-dimensional finite element modelling of bone.

    Journal of biomedical engineering·1993
    Same journal

    Three dimensional shape reconstruction and finite element analysis of femur before and after the cementless type of total hip replacement.

    Journal of biomedical engineering·1993
    Same journal

    The Rancho EMG analyzer: a computerized system for gait analysis.

    Journal of biomedical engineering·1993
    Same journal

    Preparation and in vivo evaluation of a newly developed bioglass ceramic.

    Journal of biomedical engineering·1993
    See all related articles

    This study improved speech recognition accuracy for biomedical engineering applications using adaptive template updating. An adaptive system achieved 98.8% accuracy, simplifying speaker training.

    Area of Science:

    • Biomedical Engineering
    • Computer Science
    • Signal Processing

    Background:

    • Low-cost speech recognition devices offer potential in biomedical engineering.
    • Current devices rely on speaker training and template comparison.
    • High accuracy and simplified training are crucial for practical application.

    Purpose of the Study:

    • To investigate statistical techniques for improving speech recognition accuracy.
    • To develop an adaptive system for simplifying speaker training in low-cost devices.

    Main Methods:

    • Utilized Mahalanobis distance metric for word classification.
    • Employed cluster analysis to derive templates from training data.
    • Developed an adaptive system that updates templates during normal operation to track voice changes.

    Related Experiment Videos

    Main Results:

    • Cluster analysis-based templates with Mahalanobis distance outperformed other strategies.
    • The adaptive system achieved 98.8% recognition accuracy on a 32-word vocabulary.
    • The adaptive system significantly simplified speaker training by updating templates dynamically.

    Conclusions:

    • Adaptive template updating is effective for improving speech recognition accuracy in biomedical applications.
    • Clustering principles can be applied to create efficient adaptive systems.
    • The developed adaptive system offers a practical solution for low-cost, high-accuracy speech recognition.