We acknowledge the support of the U.S. Air Force Office of Scientific Research and the U.S. Office of Naval Research in the development of this toolbox.
This toolbox contains all of the state-of-the-art methods of complex matrix factorization, including complex matrix factorization with intra-source additivity constraints (CMFWISA) and complex probabilistic latent component analysis (CPLCA). These methods are currently optimized for use with a short time Fourier transform (STFT) for single-channel source separation of audio, but can be used for any complex-valued matrix data.
B. King, “New Methods of Complex Matrix Factorization for Single-Channel Source Separation and Analysis,” University of Washington, 2012. pdf
B. King and L. Atlas, “Single-Channel Source Separation Using Complex Matrix Factorization,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 8, pp. 2591-2597, Nov. 2011. pdf
B. King and L. Atlas, “Single-channel Source Separation using Simplified-training Complex Matrix Factorization,” International Conference on Acoustics, Speech, and Signal Processing, Dallas, TX: 2010.
Use the following format to cite the Complex Matrix Factorization Toolbox in publications and reports:
Brian King and Les Atlas, Complex Matrix Factorization Toolbox Version 1.0 for MATLAB, https://sites.google.com/a/uw.edu/isdl/projects/cmf-toolbox, University of Washington,
To download the Complex Matrix Factorization Toolbox, fill out this form. A download link will be emailed to you shortly.
2012-09-10 Version 1.0 released
This code was developed by Brian King. He would love to hear your questions, comments, and ideas about the code as well as CMF in general. You can contact him at bbking(at)uw.edu.