End-to-End Text-to-Speech Using Latent Duration Based on VQ-VAE.
Yusuke YasudaXin WangJunichi YamagishiPublished in: ICASSP (2021)
Keyphrases
- end to end
- text to speech
- vector quantization
- speech synthesis
- image compression
- image coding
- prosodic features
- vector quantizer
- programming tool
- wireless ad hoc networks
- text to speech synthesis
- admission control
- multipath
- word processing
- ad hoc networks
- compressed images
- high bandwidth
- rate allocation
- wavelet transform
- application layer
- scalable video
- congestion control
- resource management
- image quality
- real time