Disentangled speaker and nuisance attribute embedding for robust speaker verification.
Woo Hyun KangSung Hwan MunMin Hyun HanNam Soo KimPublished in: CoRR (2020)
Keyphrases
- speaker verification
- noisy environments
- speaker recognition
- prosodic features
- audio visual
- speech recognition
- emotion recognition
- speaker identification
- artificial neural networks
- acoustic features
- language identification
- multi modal
- noise reduction
- using artificial neural networks
- neural network
- face verification
- vector quantization
- learning algorithm