Reducing musical noise in blind source separation by time-domain sparse filters and split bregman method.
Wenye MaMeng YuJack XinStanley J. OsherPublished in: INTERSPEECH (2010)
Keyphrases
- blind source separation
- mixing matrix
- eigenvalue decomposition
- source signals
- split bregman method
- sparse representation
- source separation
- independent component analysis
- non stationary
- blind separation
- negative matrix factorization
- frequency domain
- wiener filter
- speech signal
- missing data
- signal to noise ratio
- independent components
- active contour model
- random projections
- edge detection
- high dimensional
- face recognition
- image segmentation
- total variation
- image classification
- object recognition