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

DECTalk and MacinTalk speech synthesizers: intelligibility differences for three listener groups

K C Hustad1, R D Kent, D R Beukelman

  • 1Department of Special Education and Communication Disorders, University of Nebraska, Lincoln 68583-0731, USA. khustad@unlinfo.unl.edu

Journal of Speech, Language, and Hearing Research : JSLHR
|August 26, 1998
PubMed
Summary

Expert listeners achieved higher word intelligibility with DECTalk (Digital Equipment Corporation Text-to-Speech) than inexperienced listeners. DECTalk’s Perfect Paul voice was more intelligible than MacinTalk’s Bruce voice.

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

Multi-modal access method (eye-tracking + switch-scanning) for individuals with severe motor impairment: A preliminary investigation.

Assistive technology : the official journal of RESNA·2022
Same author

Perceptuo-acoustic assessment of prosodic impairment in dysarthria.

Clinical linguistics & phonetics·2011
Same author

Formoffa: An automated formant, moment, fundamental frequency, amplitude analysis of normal and disordered speech.

Clinical linguistics & phonetics·2010
Same author

Voice dysfunction in dysarthria: application of the Multi-Dimensional Voice Program.

Journal of communication disorders·2003
Same author

A treatment for vocal cord dysfunction in female athletes: an outcome study.

The Laryngoscope·2002
Same author

A protocol for identification of early bulbar signs in amyotrophic lateral sclerosis.

Journal of the neurological sciences·2001

Area of Science:

  • Speech synthesis technology
  • Human-computer interaction
  • Auditory perception

Background:

  • Evaluating speech synthesizer intelligibility is crucial for effective human-computer interaction.
  • Previous research has compared various speech synthesis systems, but direct comparisons between DECTalk and MacinTalk at the word level are limited.
  • Listener expertise may significantly influence the perception and intelligibility of synthesized speech.

Purpose of the Study:

  • To compare the word-level intelligibility of DECTalk and MacinTalk speech synthesizers.
  • To investigate the impact of listener expertise on speech intelligibility assessment.
  • To identify specific voice characteristics contributing to intelligibility differences.

Main Methods:

  • Utilized the Modified Rhyme Test (MRT) for word intelligibility assessment.

Related Experiment Videos

  • Employed an open-format transcription task for data collection.
  • Recruited three listener groups: inexperienced, speech-language pathologists, and speech synthesis experts.
  • Conducted between-subjects and within-subjects analyses of variance (ANOVA) to compare intelligibility scores.

    • Main Results:

    • Speech synthesis experts demonstrated significantly higher word identification accuracy compared to inexperienced listeners and speech-language pathologists.
    • Listeners exhibited superior intelligibility for the DECTalk male voice (Perfect Paul) over the MacinTalk male voice (Bruce).
    • No significant intelligibility differences were found for other gender/age-matched voice pairs between the two synthesizers.

    Conclusions:

    • Listener expertise is a critical factor in accurately assessing speech synthesizer intelligibility.
    • DECTalk's Perfect Paul voice offers enhanced intelligibility compared to MacinTalk's Bruce voice.
    • Further research should explore acoustic features contributing to intelligibility variations in speech synthesis systems.