Optimization of Deep Neural Network (DNN) Speech Coder Using a Multi Time Scale Perceptual Loss Function.
Joon ByunSeungmin ShinJongmo SungSeungkwon BeackYoungcheol ParkPublished in: INTERSPEECH (2022)
Keyphrases
- loss function
- neural network
- risk minimization
- stochastic gradient descent
- loss minimization
- pairwise
- support vector
- empirical risk
- training process
- coordinate descent method
- logistic regression
- learning to rank
- regularization term
- boosting framework
- hinge loss
- image compression
- boosting algorithms
- image coding
- back propagation
- convex loss functions
- reproducing kernel hilbert space
- bayes rule
- support vector machine
- decision trees