Deep neural network-based speaker embeddings for end-to-end speaker verification.
David SnyderPegah GhahremaniDaniel PoveyDaniel Garcia-RomeroYishay CarmielSanjeev KhudanpurPublished in: SLT (2016)
Keyphrases
- end to end
- speaker verification
- speaker recognition
- prosodic features
- noisy environments
- neural network
- audio visual
- congestion control
- multilayer perceptron
- emotion recognition
- dimensionality reduction
- low dimensional
- acoustic features
- metadata
- speaker diarization
- using artificial neural networks
- noise reduction
- computer vision