Hybrid Network with Multi-Level Global-Local Statistics Pooling for Robust Text-Independent Speaker Recognition.
Woo Hyun KangJahangir AlamAbderrahim FathanPublished in: ASRU (2021)
Keyphrases
- global information
- global image statistics
- recognition accuracy
- object recognition
- partial occlusion
- robust recognition
- feature extraction
- pattern recognition
- network structure
- recognition algorithm
- pose invariant face recognition
- computationally simple
- data sets
- peer to peer
- multi layer
- recognition rate
- network management
- action recognition
- varying illumination conditions
- illumination invariance
- character recognition
- network model
- visual recognition
- network topologies
- computationally efficient
- image sequences
- computer networks
- network architecture
- hand gestures
- network traffic
- communication networks
- community structure