Deep speaker embedding with frame-constrained training strategy for speaker verification.
Bin GuPublished in: INTERSPEECH (2022)
Keyphrases
- speaker verification
- speaker recognition
- noisy environments
- prosodic features
- audio visual
- emotion recognition
- acoustic features
- training set
- multilayer perceptron
- using artificial neural networks
- language identification
- face verification
- genetic algorithm
- noise reduction
- human computer interaction
- face recognition
- image sequences