Domain Adaptation and Autoencoder Based Unsupervised Speech Enhancement.
Yi LiYang SunKirill V. HoroshenkovSyed Mohsen NaqviPublished in: CoRR (2021)
Keyphrases
- domain adaptation
- speech enhancement
- semi supervised
- manifold alignment
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- labeled data
- semi supervised learning
- multiple sources
- cross domain
- speech signal
- transfer learning
- sentiment classification
- vocal tract
- unsupervised learning
- linear prediction
- supervised learning
- unlabeled data
- test data
- document classification
- wiener filter
- smoothing algorithm
- target domain
- pairwise
- text classification
- co training
- multi channel
- video sequences
- neural network
- active learning
- speech recognition
- frequency domain
- text categorization
- multi view
- training data
- image processing