• DocumentCode
    180333
  • Title

    Phase constrained complex NMF: Separating overlapping partials in mixtures of harmonic musical sources

  • Author

    Bronson, Jonathan ; Depalle, Philippe

  • Author_Institution
    Schulich Sch. of Music, McGill Univ., Montreal, QC, Canada
  • fYear
    2014
  • fDate
    4-9 May 2014
  • Firstpage
    7475
  • Lastpage
    7479
  • Abstract
    This paper examines complex non-negative matrix factorization (CMF) as a tool for separating overlapping partials in mixtures of harmonic musical sources. Unlike non-negative matrix factorization (NMF), CMF allows for the development of source separation procedures founded on a mixture model rooted in the complex-spectrum domain (in which the superposition of overlapping sources is preserved). This paper introduces a physically motivated phase constraint based on the assumption that the source´s pitch is sufficient in specifying the phase evolution of the harmonics over time, uniting sinusoidal modelling of acoustic sources with the CMF analysis of their spectral representations. The CMF-based separation procedure, armed with this novel phase constraint, is demonstrated to offer a superior performance to NMF when employed as a tool for separating overlapping partials in the acoustic test cases considered.
  • Keywords
    acoustic signal processing; matrix decomposition; music; signal representation; source separation; CMF analysis; CMF-based separation procedure; acoustic source sinusoidal modelling; acoustic test; complex nonnegative matrix factorization; complex-spectrum domain; harmonic musical source mixture model; motivated phase constraint; overlapping partial separation; phase constrained complex NMF; source pitch; source separation procedures; spectral representation; Acoustics; Harmonic analysis; Mathematical model; Optimization; Source separation; Speech; complex non-negative matrix factorization; harmonic resolution; non-negative matrix factorization; phase constraints; source separation;
  • 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.2014.6855053
  • Filename
    6855053