Informed monaural source separation of music based on convolutional sparse coding.
Ping-Keng JaoYi-Hsuan YangBrendt WohlbergPublished in: ICASSP (2015)
Keyphrases
- sparse coding
- source separation
- audio features
- sparse representation
- natural images
- blind source separation
- image classification
- denoising
- linear combination
- music information retrieval
- independent component analysis
- visual features
- audio visual
- unsupervised learning
- feature set
- feature space
- low level
- music retrieval
- generative model
- high dimensional
- image representation
- visual words
- image patches
- negative matrix factorization
- higher order
- face recognition
- gaussian process
- image processing
- data sets