Queen Margaret University logo
    • Login
    View Item 
    •   QMU Repositories
    • eResearch
    • School of Health Sciences
    • CASL
    • View Item
    •   QMU Repositories
    • eResearch
    • School of Health Sciences
    • CASL
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Towards ordinal classification of voice quality features with acoustic parameters

    Date
    2019-03-09
    Author
    Schaeffler, Felix
    Eichner, Matthias
    Beck, Janet M.
    Metadata
    Show full item record
    Citation
    Schaeffler, F., Eichner, M. & Beck, J. (2019) Towards ordinal classification of voice quality features with acoustic parameters. In: Proceedings of The Conference on Electronic Speech Signal Processing, TU Dresden, 6-8 March 2019. ESSV, pp. 288-295.
    Abstract
    The human voice is capable of fine-grained variation that results in listener attributions of various psychological, social and biological factors. The complexity of this process is reflected in the number and richness of terms that are used to describe human voices. In this paper we argue that any application that attempts a mapping of the acoustic voice signal onto voice descriptor labels would benefit from an intermediate auditory-phonetic level. As a point of departure we explore the relationships between acoustic parameters and some specific perceptual features derived from Vocal Profile Analysis (VPA), a phonetically motivated voice quality analysis scheme. Perceptual analysis of voice samples from 133 speakers was carried out using VPA for three key phonation features (creakiness, whisperiness, harshness). We extracted eleven acoustic parameters from the samples and used stepwise linear regression to identify acoustic parameters with predictive value. Samples from female speakers were used to derive regression equations which were then used to predict VPA ratings of male voices. Results show significant predictors for all three phonation features and indicate that predictions for the three phonation types rely mainly on different parameters. If a tolerance of ± 1 scalar degree for the perceptual analysis is accepted, then classification accuracy lies at or above 90% for all three phonation features.
    URI
    https://eresearch.qmu.ac.uk/handle/20.500.12289/10224
    URI
    http://www.essv.de/pdf/2019_288_295.pdf
    Collections
    • CASL

    Queen Margaret University: Research Repositories
    Accessibility Statement | Repository Policies | Contact Us | Send Feedback | HTML Sitemap

     

    Browse

    All QMU RepositoriesCommunities & CollectionsBy YearBy PersonBy TitleBy QMU AuthorBy Research CentreThis CollectionBy YearBy PersonBy TitleBy QMU AuthorBy Research Centre

    My Account

    LoginRegister

    Queen Margaret University: Research Repositories
    Accessibility Statement | Repository Policies | Contact Us | Send Feedback | HTML Sitemap