Constructing Time-Frequency Dictionaries for Source Separation via Time-Frequency Masking and Source Localisation

  • Ruairí de Fréin
  • Scott T. Rickard
  • Barak A. Pearlmutter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5441)


We describe a new localisation and source separation algorithm which is based upon the accurate construction of time-frequency spatial signatures. We present a technique for constructing time-frequency spatial signatures with the required accuracy. This algorithm for multi-channel source separation and localisation allows arbitrary placement of microphones yet achieves good performance. We demonstrate the efficacy of the technique using source location estimates and compare estimated time-frequency masks with the ideal 0 dB mask.


Sparse Representation Source Separation Blind Source Separation Spatial Signature Window Signal 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Malioutov, D.M., Çetin, M., Willsky, A.S.: A sparse signal reconstruction perspective for source localization with sensor arrays. IEEE Transactions on Signal Processing 53, 3010–3022 (2005)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Model, D., Zibulevsky, M.: Signal Reconstruction in Sensor Arrays using Sparse Representations. Signal Processing 86, 624–638 (2006)CrossRefMATHGoogle Scholar
  3. 3.
    Gorodnitsky, I.F., Rao, B.D.: Sparse signal reconstruction from limited data using FOCUSS: A re-weighted minimum norm algorithm. IEEE Transactions on Signal Processing 45, 600–616 (1997)CrossRefGoogle Scholar
  4. 4.
    Zibulevsky, M., Pearlmutter, B.A.: Blind source separation by sparse decomposition in a signal dictionary. Neural Computation 13, 863–882 (2001)CrossRefMATHGoogle Scholar
  5. 5.
    Reddy, A.M., Raj, B.: Soft Mask Methods for Single-Channel Speaker Separation. IEEE Transactions on Audio, Speech, and Language Processing 15, 1766–1776 (2007)CrossRefGoogle Scholar
  6. 6.
    de Frein, R., Drakakis, K., Rickard, S.T.: Portfolio diversification using subspace factorizations. In: Proceedings of the Annual Conference on Information Sciences and Systems, pp. 1075–1080 (2008)Google Scholar
  7. 7.
    Rickard, S.T.: Sparse sources are separated sources. In: Proceedings of the 16th Annual European Signal Processing Conference, Florence, Italy (2006)Google Scholar
  8. 8.
    Yilmaz, O., Rickard, S.T.: Blind separation of speech mixtures via time-frequency masking. IEEE Transactions on Signal Processing 52, 1830–1847 (2004)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Hoyer, P.O.: Non-negative sparse coding. In: Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, pp. 557–565 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ruairí de Fréin
    • 1
  • Scott T. Rickard
    • 1
  • Barak A. Pearlmutter
    • 2
  1. 1.Complex & Adaptive Systems LaboratoryUniversity College DublinIreland
  2. 2.Hamilton InstituteNational University of Ireland MaynoothCo. KildareIreland

Personalised recommendations