Low-latency real-time non-parallel voice conversion based on cyclic variational autoencoder and multiband WaveRNN with data-driven linear prediction.
Patrick Lumban TobingTomoki TodaPublished in: SSW (2021)
Keyphrases
- low latency
- linear prediction
- multi band
- real time
- high speed
- virtual machine
- image coding
- high throughput
- highly efficient
- speech signal
- multispectral
- prediction error
- lossless compression
- subband
- image segmentation
- frequency band
- machine learning
- hyperspectral
- microarray
- autoregressive
- maximum entropy
- graphical models
- high quality