Few-Shot Speaker Identification Using Depthwise Separable Convolutional Network with Channel Attention.
Yanxiong LiWucheng WangHao ChenWenchang CaoWei LiQianhua HePublished in: Odyssey (2022)
Keyphrases
- speaker identification
- convolutional network
- speech recognition
- gaussian mixture model
- convolutional neural networks
- noisy environments
- feature extraction
- speech signal
- broadcast news
- video data
- video sequences
- feature extractor
- key frames
- coarse to fine
- pattern recognition
- edge detection
- maximum likelihood
- information retrieval
- face recognition