Neural speech-rate conversion with multispeaker WaveNet vocoder.
Takuma OkamotoKeisuke MatsubaraTomoki TodaYoshinori ShigaHisashi KawaiPublished in: Speech Commun. (2022)
Keyphrases
- speech recognition
- network architecture
- audio visual
- neural network
- speech synthesis
- real time
- speech signal
- speaker verification
- language acquisition
- spoken language
- nonlinear predictive control
- neural fuzzy
- vocal tract
- speaker recognition
- growth rate
- neural model
- noisy environments
- dialogue system
- learning rules
- bio inspired
- pattern recognition