• DocumentCode
    179094
  • Title

    Sparse component analysis via dyadic cyclic descent

  • Author

    Ulfarsson, Magnus Orn ; Solo, Victor

  • Author_Institution
    Dept. Electr. Eng., Univ. of Iceland, Reykjavik, Iceland
  • fYear
    2014
  • fDate
    4-9 May 2014
  • Firstpage
    4234
  • Lastpage
    4238
  • Abstract
    Sparse component analysis (SCA) is a widely used method for solving the blind source separation problem. We develop a new cyclic descent algorithm for SCA based on a dyadic expansion. To select the associated tuning parameter a method based on the Bayesian information criterion is developed. In simulations the new algorithm is compared with state of the art algorithms from the literature.
  • Keywords
    Bayes methods; blind source separation; function approximation; Bayesian information criteria; blind source separation problem; cyclic descent algorithm; dyadic cyclic descent; dyadic expansion; sparse component analysis; Algorithm design and analysis; Educational institutions; Signal processing algorithms; Signal to noise ratio; Speech; Tuning; Vectors; Cyclic Descent; Sparse Component Analysis; Sparsity;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
  • Conference_Location
    Florence
  • Type

    conf

  • DOI
    10.1109/ICASSP.2014.6854400
  • Filename
    6854400
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=179094