Adversarial defense for automatic speaker verification by cascaded self-supervised learning models.
Haibin WuXu LiAndy T. LiuZhiyong WuHelen MengHung-yi LeePublished in: CoRR (2021)
Keyphrases
- learning models
- speaker verification
- machine learning
- learning algorithm
- noisy environments
- semi supervised learning
- machine learning algorithms
- classification models
- learning problems
- loss function
- face detection
- conditional random fields
- learning tasks
- emotion recognition
- audio visual
- information retrieval
- data sets
- natural language processing
- supervised learning
- support vector
- face verification
- neural network