Loss Functions for Deep Monaural Speech Enhancement.
Jan FreiwaldLea SchönherrChristopher SchymuraSteffen ZeilerDorothea KolossaPublished in: IJCNN (2020)
Keyphrases
- loss function
- speech enhancement
- noise reduction
- noisy environments
- signal to noise ratio
- single channel
- speech signal
- pairwise
- support vector
- linear prediction
- loss minimization
- learning to rank
- vocal tract
- multi channel
- background noise
- smoothing algorithm
- wiener filter
- reproducing kernel hilbert space
- speech recognition
- convex loss functions
- risk minimization
- information retrieval
- additive noise
- pattern recognition
- prediction error
- image coding
- cross validation
- higher order
- prior knowledge