A feature survey for emotion classification of western popular music

Scott Beveridge, Don Knox

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper we propose a feature set for emotion classification of Western popular music. We show that by surveying a range of common feature extraction methods, a set of five features can model emotion with good accuracy. To evaluate the system we implement an independent feature evaluation paradigm aimed at testing the property of generalizability; the ability of a machine learning algorithm to maintain good performance over different data sets.
    Original languageEnglish
    Title of host publicationThe 9th International Symposium on Computer Music Modeling and Retrieval (CMMR) Music and Emotions
    PublisherSpringer-Verlag
    Pages508-517
    Number of pages10
    Publication statusPublished - Jun 2012

    Publication series

    NameLecture Notes in Computer Sciences
    PublisherSpringer

    Keywords

    • music emotion classification
    • popular music
    • support vector machine

    Fingerprint Dive into the research topics of 'A feature survey for emotion classification of western popular music'. Together they form a unique fingerprint.

    Cite this