Phonetic-attention scoring for deep speaker features in speaker verification.
Lantian LiZhiyuan TangYing ShiDong WangPublished in: CoRR (2018)
Keyphrases
- speaker verification
- speaker recognition
- noisy environments
- prosodic features
- feature vectors
- speech recognition
- acoustic features
- audio visual
- multilayer perceptron
- pattern recognition
- feature space
- emotion recognition
- feature extraction
- feature set
- language identification
- low level
- learning algorithm
- user interface
- artificial neural networks
- using artificial neural networks
- video sequences
- multiscale
- mel frequency cepstral coefficients