Harmonic variable-size dictionary learning for music source separation.
Steven K. TjoaMatthew C. StammW. Sabrina LinK. J. Ray LiuPublished in: ICASSP (2010)
Keyphrases
- dictionary learning
- variable size
- source separation
- audio features
- sparse representation
- blind source separation
- sparse coding
- fixed size
- independent component analysis
- music information retrieval
- denoising
- visual features
- music retrieval
- audio visual
- sliding window
- image classification
- low level
- feature set
- negative matrix factorization
- signal processing
- computer vision
- unsupervised learning
- image processing
- image representation
- multiscale