MURAL - Maynooth University Research Archive Library



    Discovering speech phones using convolutive non-negative matrix factorisation with a sparseness constraint


    O'Grady, Paul D. and Pearlmutter, Barak A. (2008) Discovering speech phones using convolutive non-negative matrix factorisation with a sparseness constraint. Neurocomputing, 72 (1-3). pp. 88-101.

    [img] Download (487kB)


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can be constructed by Non-negative Matrix Factorisation (NMF), a method for finding parts-based representations of non-negative data. Here, we present an extension to convolutive NMF that includes a sparseness constraint, where the resultant algorithm has multiplicative updates and utilises the beta divergence as its reconstruction objective. In combination with a spectral magnitude transform of speech, this method discovers auditory objects that resemble speech phones along with their associated sparse activation patterns. We use these in a supervised separation scheme for monophonic mixtures, finding improved separation performance in comparison to classic convolutive NMF.

    Item Type: Article
    Keywords: Non-negative matrix factorisation; Sparse representations; Convolutive; Hamilton Institute; dictionaries; Speech phone analysis;
    Academic Unit: Faculty of Science and Engineering > Research Institutes > Hamilton Institute
    Item ID: 1685
    Depositing User: Hamilton Editor
    Date Deposited: 25 Nov 2009 12:50
    Journal or Publication Title: Neurocomputing
    Publisher: Elsevier
    Refereed: Yes
    URI:

      Repository Staff Only(login required)

      View Item Item control page

      Downloads

      Downloads per month over past year