• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    Onsets, activity, and events: a multi-task approach for polyphonic sound event modelling 
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • Onsets, activity, and events: a multi-task approach for polyphonic sound event modelling
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • Onsets, activity, and events: a multi-task approach for polyphonic sound event modelling
    ‌
    ‌

    Browse

    All of QMROCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects
    ‌
    ‌

    Administrators only

    Login
    ‌
    ‌

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Onsets, activity, and events: a multi-task approach for polyphonic sound event modelling

    View/Open
    Accepted version (281.8Kb)
    Pagination
    174 - 178
    Publisher URL
    http://dcase.community/workshop2019/
    Metadata
    Show full item record
    Abstract
    State of the art polyphonic sound event detection (SED) systems function as frame-level multi-label classification models. In the context of dynamic polyphony levels at each frame, sound events interfere with each other which degrade a classifier's ability to learn the exact frequency profile of individual sound events. Frame-level localized classifiers also fail to explicitly model the long-term temporal structure of sound events. Consequently, the event-wise detection performance is less than the segment-wise detection. We define 'temporally precise polyphonic sound event detection' as the subtask of detecting sound event instances with the correct onset. Here, we investigate the effectiveness of sound activity detection (SAD) and onset detection as auxiliary tasks to improve temporal precision in polyphonic SED using multi-task learning. SAD helps to differentiate event activity frames from noisy and silence frames and helps to avoid missed detections at each frame. Onset predictions ensure the start of each event which in turn are used to condition predictions of both SAD and SED. Our experiments on the URBAN-SED dataset show that by conditioning SED with onset detection and SAD, there is over a three-fold relative improvement in event-based F-score.
    Authors
    Pankajakshan, A; Bear, H; Benetos, E; 4th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2019)
    URI
    https://qmro.qmul.ac.uk/xmlui/handle/123456789/59659
    Collections
    • Electronic Engineering and Computer Science [2318]
    Copyright statements
    © The Author(s) 2019
    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.