Investigating Cross-Domain Losses for Speech Enhancement.
Sherif AbdulatifKarim ArmaniousJayasankar T. SajeevKarim GuirguisBin YangPublished in: CoRR (2020)
Keyphrases
- cross domain
- speech enhancement
- noise reduction
- noisy environments
- signal to noise ratio
- single channel
- speech signal
- knowledge transfer
- linear prediction
- transfer learning
- domain adaptation
- text categorization
- vocal tract
- background noise
- multi channel
- smoothing algorithm
- wiener filter
- target domain
- information retrieval
- e government
- multiresolution
- data mining
- additive noise
- prior information
- speech recognition
- active learning