On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement.
Ashutosh PandeyDeLiang WangPublished in: CoRR (2020)
Keyphrases
- deep learning
- speech enhancement
- noise reduction
- noisy environments
- signal to noise ratio
- unsupervised learning
- single channel
- speech signal
- machine learning
- vocal tract
- linear prediction
- weakly supervised
- wiener filter
- smoothing algorithm
- prior information
- signal processing
- background noise
- semi supervised
- training set
- similarity measure