Spectrogram dimensionality reductionwith independence constraints

We present an algorithm to find a low-dimensional decomposition of a spectrogram by formulating this as a regularized non-negative matrix factorization (NMF) problem with a regularization term chosen to encourage independence. This algorithm provides a better decomposition than standard NMF when the underlying sources are independent. It is directly applicable to non-square matrices, and it makes better use of additional observation streams than previous nonnegative ICA algorithms.

[1]  Bhiksha Raj,et al.  Speech denoising using nonnegative matrix factorization with priors , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[3]  Andrzej Cichocki,et al.  New Algorithms for Non-Negative Matrix Factorization in Applications to Blind Source Separation , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[4]  Mark D. Plumbley.  Conditions for nonnegative independent component analysis , 2002, IEEE Signal Processing Letters.

[5]  Bhiksha Raj,et al.  Regularized non-negative matrix factorization with temporal dependencies for speech denoising , 2008, INTERSPEECH.

[6]  Erkki Oja,et al.  Blind Separation of Positive Sources by Globally Convergent Gradient Search , 2004, Neural Computation.

[7]  C. Fancourt,et al.  A comparison of decorrelation criteria for the blind source separation of nonstationary signals , 2002, Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2002.

[8]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

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