WaveFlow: A Compact Flow-based Model for Raw Audio

In this work, we present WaveFlow, a small-footprint generative flow for raw audio, which is trained with maximum likelihood without probability density distillation and auxiliary losses as used in Parallel WaveNet and ClariNet. It provides a unified view of likelihood-based models for raw audio, including WaveNet and WaveGlow as special cases. We systematically study these likelihood-based generative models for raw waveforms in terms of test likelihood and speech fidelity. We demonstrate that WaveFlow can synthesize high-fidelity speech as WaveNet, while only requiring a few sequential steps to generate very long waveforms with hundreds of thousands of time-steps. Furthermore, WaveFlow closes the significant likelihood gap that has existed between autoregressive models and flow-based models for efficient synthesis. Finally, our small-footprint WaveFlow has 5.91M parameters and can generate 22.05kHz high-fidelity speech 42.6 times faster than real-time on a GPU without engineered inference kernels.