Speaker verification using attentive multi-scale convolutional recurrent network.
Yanxiong LiZhongjie JiangWenchang CaoQisheng HuangPublished in: Appl. Soft Comput. (2022)
Keyphrases
- speaker verification
- recurrent networks
- multiscale
- recurrent neural networks
- noisy environments
- feed forward
- neural network
- audio visual
- speaker recognition
- biologically inspired
- prosodic features
- multilayer perceptron
- natural images
- emotion recognition
- visual attention
- image processing
- image segmentation
- language identification
- artificial neural networks
- back propagation
- image representation
- noise reduction
- edge detection
- human computer interaction