Skip to main navigation Skip to search Skip to main content

Improving the intelligibility of dysarthric speech

  • Alexander B. Kain
  • , John Paul Hosom
  • , Xiaochuan Niu
  • , Jan P.H. van Santen
  • , Melanie Fried-Oken
  • , Janice Staehely

Research output: Contribution to journalArticlepeer-review

Abstract

Dysarthria is a speech motor disorder usually resulting in a substantive decrease in speech intelligibility by the general population. In this study, we have significantly improved the intelligibility of dysarthric vowels of one speaker from 48% to 54%, as evaluated by a vowel identification task using 64 CVC stimuli judged by 24 listeners. Improvement was obtained by transforming the vowels of a speaker with dysarthria to more closely match the vowel space of a non-dysarthric (target) speaker. The optimal mapping feature set, from a list of 21 candidate feature sets, proved to be one utilizing vowel duration and F1-F3 stable points, which were calculated using shape-constrained isotonic regression. The choice of speaker-specific or speaker-independent vowel formant targets appeared to be insignificant. Comparisons with "oracle" conditions were performed in order to evaluate the analysis/re-synthesis system independently of the transformation function.

Original languageEnglish (US)
Pages (from-to)743-759
Number of pages17
JournalSpeech Communication
Volume49
Issue number9
DOIs
StatePublished - Sep 2007

Funding

This research was conducted with support from NSF Grant 0117911 “Making Dysarthric Speech Intelligible”. Oregon Health & Science University (OHSU), Dr. Kain, Dr. Hosom, and Dr. Jan van Santen have a significant financial interest in BioSpeech, Inc., a company that may have a commercial interest in the results of this research and technology. This potential conflict was reviewed and a management plan approved by the OHSU Conflict of Interest in Research Committee and the Integrity Program Oversight Council was implemented.

Funders
Author National Science Foundation National Science Foundation National Institutes of Health National Institutes of Health National Institutes of Health National Institutes of Health National Science Foundation National Science Foundation

    Keywords

    • Dysarthria
    • Intelligibility
    • Speech modification
    • Speech processing
    • Speech transformation

    ASJC Scopus subject areas

    • Software
    • Modeling and Simulation
    • Communication
    • Language and Linguistics
    • Linguistics and Language
    • Computer Vision and Pattern Recognition
    • Computer Science Applications

    Fingerprint

    Dive into the research topics of 'Improving the intelligibility of dysarthric speech'. Together they form a unique fingerprint.

    Cite this