On Spectral Basis Selection for Single Channel Polyphonic Music Separation

In this paper we present a method of separating musical instrument sound sources from their monaural mixture, where we take the harmonic structure of music into account and use the sparseness and the overlapping NMF to select representative spectral basis vectors which are used to reconstruct unmixed sound. A method of spectral basis selection is illustrated and experimental results with monaural instantaneous mixtures of voice/cello and saxophone/viola, are shown to confirm the validity of our proposed method.

[1]  J. Eggert,et al.  Transformation-invariant representation and NMF , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[2]  Allan Kardec Barros,et al.  Independent Component Analysis and Blind Source Separation , 2007, Signal Processing.

[3]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[4]  Seungjin Choi,et al.  Nonnegative features of spectro-temporal sounds for classification , 2005, Pattern Recognit. Lett..

[5]  Paris Smaragdis,et al.  Non-negative Matrix Factor Deconvolution; Extraction of Multiple Sound Sources from Monophonic Inputs , 2004, ICA.

[6]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[7]  P. Smaragdis,et al.  Non-negative matrix factorization for polyphonic music transcription , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[8]  Patrik O. Hoyer,et al.  Non-negative Matrix Factorization with Sparseness Constraints , 2004, J. Mach. Learn. Res..

[9]  Mark D. Plumbley,et al.  Automatic Music Transcription and Audio Source Separation , 2002, Cybern. Syst..