Progressive loss functions for speech enhancement with deep neural networks.
Jorge LlombartDayana RibasAntonio MiguelLuis VicenteAlfonso OrtegaEduardo LleidaPublished in: EURASIP J. Audio Speech Music. Process. (2021)
Keyphrases
- loss function
- speech enhancement
- neural network
- noise reduction
- pairwise
- noisy environments
- signal to noise ratio
- single channel
- speech signal
- learning to rank
- loss minimization
- support vector
- linear prediction
- pattern recognition
- reproducing kernel hilbert space
- risk minimization
- speech recognition
- wavelet transform
- background noise
- smoothing algorithm
- boosting algorithms
- wiener filter
- vocal tract
- multiresolution
- multi channel
- image coding
- probabilistic model