Geometrical understanding of the PCA subspace method for overdetermined blind source separation.
Stefan WinterHiroshi SawadaShoji MakinoPublished in: ICASSP (2) (2003)
Keyphrases
- blind source separation
- subspace methods
- independent component analysis
- non stationary
- negative matrix factorization
- principal component analysis
- blind separation
- independent components
- factor analysis
- sparse representation
- speech signal
- signal processing
- computer vision
- frequency domain
- recommender systems
- feature space
- feature extraction