TR2007-002

Convolutive Speech Bases and their Application to Supervised Speech Separation


    •  Smaragdis, P., "Convolutive Speech Bases and their Application to Supervised Speech Separation", IEEE Transactions on Audio, Speech and Language Processing, ISSN: 1558-7916, Vol. 15, No. 1, pp. 1-12, January 2007.
      BibTeX Download PDF
      • @article{Smaragdis2007jan2,
      • author = {Smaragdis, P.},
      • title = {Convolutive Speech Bases and their Application to Supervised Speech Separation},
      • journal = {IEEE Transactions on Audio, Speech and Language Processing},
      • year = 2007,
      • volume = 15,
      • number = 1,
      • pages = {1--12},
      • month = jan,
      • issn = {1558-7916},
      • url = {http://www.merl.com/publications/TR2007-002}
      • }
  • Research Areas:

    Multimedia, Speech & Audio


In this paper we present a convolutive basis decomposition method and its application on simultaneous speakers separation from monophonic recordings. The model we propose is a convolutive version of the non-negative matrix factorization algorithm. Due to the non-negativity constraint this type of coding is very well suited for intuitively and efficiently representing magnitude spectra. We present results that reveal the nature of these basis functions and we introduce their utility in separating monophonic mixtures of known speakers.