Improving Robustness of Deep Learning Based Monaural Speech Enhancement Against Processing Artifacts.
Ke TanDeLiang WangPublished in: ICASSP (2020)
Keyphrases
- deep learning
- speech enhancement
- unsupervised learning
- noise reduction
- noisy environments
- machine learning
- signal to noise ratio
- mental models
- d objects
- weakly supervised
- image processing
- bayesian networks
- pairwise
- higher order
- data mining
- training data
- speech signal
- feature extraction
- computer vision
- wiener filter
- single channel