Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-end Speaker Verification.
Gautam BhattacharyaJoão MonteiroMd. Jahangir AlamPatrick KennyPublished in: ICASSP (2019)
Keyphrases
- end to end
- speaker verification
- noisy environments
- high bandwidth
- internet protocol
- speaker recognition
- wireless ad hoc networks
- prosodic features
- audio visual
- emotion recognition
- admission control
- noise reduction
- ad hoc networks
- text localization and recognition
- congestion control
- differentiated services
- speech recognition
- using artificial neural networks
- speaker identification
- speech signal
- language identification
- multilayer perceptron
- multiscale
- gaussian mixture model
- low level