Title :
Convolutive Speech Bases and Their Application to Supervised Speech Separation
Author :
Smaragdis, Paris
Author_Institution :
Mitsubishi Electr. Res. Labs., Cambridge, MA
Abstract :
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 nonnegative matrix factorization algorithm. Due to the nonnegativity 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
Keywords :
convolution; matrix decomposition; speech coding; convolutive basis decomposition method; convolutive speech; magnitude spectra; monophonic recordings; nonnegative matrix factorization algorithm; nonnegativity constraint; speakers separation; supervised speech separation; Context modeling; Higher order statistics; Independent component analysis; Matrix decomposition; Principal component analysis; Singular value decomposition; Source separation; Speech; Supervised learning; Unsupervised learning; Convolutive bases; nonnegative matrix factorization; source separation;
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
DOI :
10.1109/TASL.2006.876726
