Title :
Spectrogram dimensionality reductionwith independence constraints
Author :
Wilson, Kevin W. ; Raj, Bhiksha
Author_Institution :
Mitsubishi Electr. Res. Lab., Cambridge, MA, USA
Abstract :
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.
Keywords :
independent component analysis; matrix decomposition; signal processing; independence constraints; independent component analysis; nonnegative ICA algorithms; nonnegative matrix factorization; spectrogram dimensionality reduction; Algorithm design and analysis; Decorrelation; Independent component analysis; Matrix decomposition; Random variables; Signal to noise ratio; Spectrogram; Vectors; matrix decomposition;
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2010.5495308