Three-stage speaker verification architecture in emotional talking environments.
Ismail ShahinAli Bou NassifPublished in: Int. J. Speech Technol. (2018)
Keyphrases
- speaker verification
- emotion recognition
- speaker recognition
- noisy environments
- prosodic features
- human computer interaction
- language identification
- multilayer perceptron
- face verification
- neural network
- genetic algorithm
- facial expressions
- principal component analysis
- language model
- gaussian mixture model
- audio visual