Supervised single-channel speech dereverberation and denoising using a two-stage model based sparse representation.
Long ZhangXu XuHuang ChenJiaxu ChenZhongfu YePublished in: Speech Commun. (2018)
Keyphrases
- sparse representation
- single channel
- denoising
- speech enhancement
- wiener filter
- frequency domain
- multi channel
- dictionary learning
- image denoising
- signal processing
- image classification
- noisy images
- sparse coding
- face recognition
- wavelet domain
- independent component analysis
- image processing
- image patches
- total variation
- natural images
- wavelet decomposition
- speech recognition
- semi supervised
- image representation
- speech signal
- high dimensional data
- unsupervised learning
- noise reduction
- feature selection
- dimensionality reduction
- compressed sensing
- spatial domain
- prior information
- feature extraction
- additive noise
- range images
- signal to noise ratio
- data sets
- image compression
- high dimensional
- machine learning