Document Type

Conference Paper


Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence


Electrical and electronic engineering

Publication Details

Accepted for publication at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Prague, 2011


Non-negative Matrix Factorization (NMF) has found use in single
channel separation of audio signals, as it gives a parts-based decom-
position of audio spectrograms where the parts typically correspond
to individual notes or chords. However, a notable shortcoming of
NMF is the need to cluster the basis functions to their sources af-
ter decomposition. Despite recent improvements in algorithms for
clustering the basis functions to sources, much work still remains to
further improve these algorithms. To this end we present a novel
clustering algorithm which overcomes some of the limitations of
previous clustering methods. This involves the use of Shifted Non-
negative Matrix Factorization (SNMF) as a means of clustering the
frequency basis functions obtained from NMF. Results show that this
gives improved clustering of pitched basis functions over previous


ABBEST Scholarship by DIT