A Novel Research to Artificial Bandwidth Extension Based on Deep BLSTM Recurrent Neural Networks and Exemplar-Based Sparse Representation.
Bin LiuJianhua TaoPublished in: INTERSPEECH (2016)
Keyphrases
- sparse representation
- recurrent neural networks
- dictionary learning
- sparse coding
- neural network
- recurrent networks
- image classification
- feed forward
- reservoir computing
- joint optimization
- compressive sensing
- echo state networks
- regularized least squares
- compressed sensing
- face recognition
- image representation
- piecewise smooth
- artificial neural networks
- negative matrix factorization
- random projections
- signal processing
- high dimensional data
- dimensionality reduction
- image patches
- norm minimization
- sparse reconstruction
- sparse approximations
- test images
- feature vectors
- pattern recognition
- multiscale
- image reconstruction