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

The effect of automatic speech recognition systems on speaking workload and task efficiency.

J M Rieger1

  • 1Faculty of Rehabilitation Medicine, University of Alberta and Craneofacial Osseointegration and Maxillofacial Prosthetic Rehabilitaion Unit (COMPRU), Edmonton, Alberta, Canada. jana.rieger@ualberta.ca

Disability and Rehabilitation
|March 8, 2003
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

The relationship between lingual and hypoglossal nerve function and quality of life in head and neck cancer.

Journal of oral rehabilitation·2013
Same author

Sensory outcomes of the anterior tongue after lingual nerve repair in oropharyngeal cancer.

Journal of oral rehabilitation·2011
Same author

A2A adenosine receptor (AR) activation inhibits pro-inflammatory cytokine production by human CD4+ helper T cells and regulates Helicobacter-induced gastritis and bacterial persistence.

Mucosal immunology·2009
Same author

Establishing a reliable protocol to measure tongue sensation.

Journal of oral rehabilitation·2007
Same author

Mouse spinal cord compression injury is reduced by either activation of the adenosine A2A receptor on bone marrow-derived cells or deletion of the A2A receptor on non-bone marrow-derived cells.

Neuroscience·2006
Same author

Functional outcomes after organ preservation treatment in head and neck cancer: a critical review of the literature.

International journal of oral and maxillofacial surgery·2006

Automatic speech recognition (ASR) software increases speech workload and reduces dictation efficiency for all users, regardless of spinal cord injury (SCI). Discrete-word ASR poses a higher risk of laryngeal overuse due to increased energy expenditure.

Area of Science:

  • Speech-language pathology
  • Human-computer interaction
  • Rehabilitation engineering

Background:

  • Automatic Speech Recognition (ASR) is increasingly used for dictation.
  • Understanding the impact of ASR on speech production is crucial for user adaptation and health.
  • Individuals with spinal cord injury (SCI) may have unique speech production needs.

Purpose of the Study:

  • To investigate speech-production behaviors during ASR dictation in individuals with and without SCI.
  • To compare speech workload and efficiency across different ASR types (continuous-speech, discrete-word) and no ASR.
  • To identify potential risks associated with ASR use, particularly for laryngeal health.

Main Methods:

  • Twelve participants (6 with SCI, 6 able-bodied) completed dictation tasks.

Related Experiment Videos

  • Tasks included spontaneous and scripted speech using continuous-speech ASR, discrete-word ASR, and no ASR.
  • Speech variables analyzed: syllables per breath group, breath group frequency, apnea frequency, dictation time, and words spoken.

    • Main Results:

    • ASR dictation significantly altered speech patterns compared to no ASR.
    • Both ASR types reduced syllables per breath group and increased breath group/apnea frequency, with discrete-word ASR showing greater differences.
    • ASR dictation required more time and produced more words, indicating increased speaker effort and reduced efficiency.

    Conclusions:

    • ASR use, especially discrete-word ASR, increases speech workload and energy expenditure.
    • Prolonged ASR use may lead to laryngeal overuse, particularly for individuals with SCI.
    • Human factors considerations are vital for optimizing ASR interfaces and minimizing user strain.