Memory Layers with Multi-Head Attention Mechanisms for Text-Dependent Speaker Verification.
Victoria MingoteAntonio MiguelAlfonso Ortega GiménezEduardo LleidaPublished in: ICASSP (2021)
Keyphrases
- speaker verification
- noisy environments
- language identification
- speaker recognition
- prosodic features
- information retrieval
- multilayer perceptron
- audio visual
- using artificial neural networks
- emotion recognition
- text data
- noise reduction
- keywords
- image processing
- face verification
- focus of attention
- text mining
- low level