Deep Speaker Embedding Extraction with Channel-Wise Feature Responses and Additive Supervision Softmax Loss Function.
Jianfeng ZhouTao JiangZheng LiLin LiQingyang HongPublished in: INTERSPEECH (2019)
Keyphrases
- loss function
- pairwise
- support vector
- learning to rank
- stochastic gradient descent
- logistic regression
- risk minimization
- empirical risk
- information extraction
- regularization term
- multi class
- convex loss functions
- feature vectors
- reproducing kernel hilbert space
- hinge loss
- image restoration
- feature extraction
- weight vector
- boosting framework