A structured nonnegative matrix factorization for source separation.
Clement LarocheMatthieu KowalskiHélène PapadopoulosGaël RichardPublished in: EUSIPCO (2015)
Keyphrases
- nonnegative matrix factorization
- source separation
- negative matrix factorization
- blind source separation
- independent component analysis
- data representation
- matrix factorization
- principal component analysis
- denoising
- temporal structure
- least squares
- document clustering
- single channel
- machine learning
- structured data
- spectral clustering
- original data
- objective function
- recommender systems
- dimensionality reduction
- nearest neighbor
- feature selection