Self-Supervised Speaker Recognition Training using Human-Machine Dialogues.
Metehan CekicRuirui LiZeya ChenYuguang YangAndreas StolckeUpamanyu MadhowPublished in: ICASSP (2022)
Keyphrases
- human machine
- speaker recognition
- spoken dialogue systems
- gaussian mixture model
- vector quantization
- speaker verification
- probabilistic neural network
- human operators
- human machine interaction
- speaker identification
- dialogue system
- neural network
- image processing
- speech recognition
- multi domain
- speech signal
- model selection
- em algorithm
- supervised learning
- user interface