Cross-Speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis.
Shifeng PanLei HePublished in: Interspeech (2021)
Keyphrases
- speech synthesis
- prosodic features
- speech recognition
- vocal tract
- text to speech
- network architecture
- automatic speech recognition
- neural network
- speech corpus
- transfer learning
- hidden markov models
- nonlinear predictive control
- speaker identification
- knowledge transfer
- language model
- information retrieval
- speaker dependent
- noisy environments
- neural model
- biologically plausible
- bio inspired
- speaker diarization
- associative memory
- image processing
- learning algorithm
- speech signal
- feature selection