• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    Gaussian Process Modelling for Audio Signals 
    •   QMRO Home
    • Queen Mary University of London Theses
    • Theses
    • Gaussian Process Modelling for Audio Signals
    •   QMRO Home
    • Queen Mary University of London Theses
    • Theses
    • Gaussian Process Modelling for Audio Signals
    ‌
    ‌

    Browse

    All of QMROCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects
    ‌
    ‌

    Administrators only

    Login
    ‌
    ‌

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Gaussian Process Modelling for Audio Signals

    View/Open
    WILKINSON_W_J_PhD_Final_041019.pdf (2.087Mb)
    Publisher
    Queen Mary University of London
    Metadata
    Show full item record
    Abstract
    Audio signals are characterised and perceived based on how their spectral make-up changes with time. Uncovering the behaviour of latent spectral components is at the heart of many real-world applications involving sound, but is a highly ill-posed task given the infi nite number of ways any signal can be decomposed. This motivates the use of prior knowledge and a probabilistic modelling paradigm that can characterise uncertainty. This thesis studies the application of Gaussian processes to audio, which offer a principled non-parametric way to specify probability distributions over functions whilst also encoding prior knowledge. Along the way we consider what prior knowledge we have about sound, the way it behaves, and the way it is perceived, and write down these assumptions in the form of probabilistic models. We show how Bayesian time-frequency analysis can be reformulated as a spectral mixture Gaussian process, and utilise modern day inference methods to carry out joint time-frequency analysis and nonnegative matrix factorisation. Our reformulation results in increased modelling flexibility, allowing more sophisticated prior knowledge to be encoded, which improves performance on a missing data synthesis task. We demonstrate the generality of this paradigm by showing how the joint model can additionally be applied to both denoising and source separation tasks without modi cation. We propose a hybrid statistical-physical model for audio spectrograms based on observations about the way amplitude envelopes decay over time, as well as a nonlinear model based on deep Gaussian processes. We examine the benefi ts of these methods, all of which are generative in the sense that novel signals can be sampled from the underlying models, allowing us to consider the extent to which they encode the important perceptual characteristics of sound.
    Authors
    Wilkinson, W
    URI
    https://qmro.qmul.ac.uk/xmlui/handle/123456789/61329
    Collections
    • Theses [3090]
    Licence information
    The copyright of this thesis rests with the author and no quotation from it or information derived from it may be published without the prior written consent of the author
    Twitter iconFollow QMUL on Twitter
    Twitter iconFollow QM Research
    Online on twitter
    Facebook iconLike us on Facebook
    • Site Map
    • Privacy and cookies
    • Disclaimer
    • Accessibility
    • Contacts
    • Intranet
    • Current students

    Modern Slavery Statement

    Queen Mary University of London
    Mile End Road
    London E1 4NS
    Tel: +44 (0)20 7882 5555

    © Queen Mary University of London.