Supervised single-channel speech enhancement using ratio mask with joint dictionary learning.
Long ZhangGuangzhao BaoJing ZhangZhongfu YePublished in: Speech Commun. (2016)
Keyphrases
- dictionary learning
- single channel
- speech enhancement
- multi channel
- sparse representation
- independent component analysis
- prior information
- wiener filter
- noise reduction
- wavelet decomposition
- signal to noise ratio
- frequency domain
- signal processing
- noisy environments
- unsupervised learning
- multiresolution
- brain activity
- vocal tract
- face recognition
- speech signal
- heart rate
- high dimensional
- pattern recognition