Supervised Separation of Speech from Background Piano Music using a Nonnegative Matrix Factorization Approach.
A. Martinez-ColónFrancisco J. Cañadas-QuesadaPedro Vera-CandeasNicolás Ruiz-ReyesF. Moreno-FuentesPublished in: STAIRS (2014)
Keyphrases
- nonnegative matrix factorization
- probabilistic latent semantic indexing
- negative matrix factorization
- semi supervised
- polyphonic music
- musical instruments
- data representation
- matrix factorization
- principal component analysis
- nonnegative matrix
- least squares
- audio features
- speech signal
- spectral clustering
- document clustering
- supervised learning
- original data
- unsupervised learning
- objective function
- learning algorithm
- data sets
- audio visual
- audio signal
- musical instrument
- feature selection
- face recognition
- image sequences
- clustering algorithm
- image processing