Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation.
Nobuyuki MoriokaHeiga ZenNanxin ChenYu ZhangYifan DingPublished in: CoRR (2022)
Keyphrases
- text to speech
- speaker adaptation
- speech synthesis
- speech recognition
- vocal tract
- maximum likelihood
- automatic speech recognition
- prosodic features
- speaker dependent
- video sequences
- programming tool
- speech recognizer
- video shots
- text to speech synthesis
- word processing
- video content
- speaker independent
- video data
- key frames
- pattern recognition
- neural network
- speech signal
- image acquisition
- image processing
- computer vision